Ole-Christoffer Granmo

• Thangaraj, Priya; Bethi, Pardhasaradhi; Granmo, Ole-Christoffer & Cenkeramaddi, Linga Reddy (2026). Clustering-based Significance-Aware Automated Data Binarization Framework for Tsetlin Machines. IEEE Transactions on Artificial Intelligence (TAI). doi: 10.1109/TAI.2026.3737096. Fulltekst i vitenarkiv Vis sammendrag

  The Tsetlin machine (TM) is an interpretable machine learning (ML) algorithm that requires relatively modest computational resources. While most ML models use continuous data representations, TM operates on binary inputs. Binarization of continuous data via brute-force thresholding has shown promising accuracy but can be computationally expensive and hinder generalization. Moreover, traditional binarization approaches, such as mean, median, and fixed thresholds, yield single-bit representations. Multi-bit representations, such as quantile, histogram, and standard binarization, are more expressive, but typically require manual definition of the number of threshold levels or the number of bits per feature. However, not all features require the same number of bits, nor do they contribute equally to prediction. To address this, we propose a simple and adaptive binarization framework that automatically determines how each feature should be represented based on its data characteristics. Instead of relying on fixed thresholds. This method identifies meaningful groups within each feature and encodes them accordingly, resulting in a more informative and balanced representation. In this paper, we propose a significance-aware adaptive binarization framework for TM learning based on k-means clustering. Each feature is individually analyzed using the Silhouette score to determine its optimal clustering structure. Features are then one-hot encoded according to their cluster partitions, resulting in a significance-aware binarized representation. All the binarized features are concatenated to form the final input for the TM. To ensure scalability, the framework includes an efficient mechanism to handle large datasets while maintaining consistency in the encoding process. To reduce the complexity of clustering, we propose a chunk-based centroid-to-centroid association mechanism, efficiently solved using the Hungarian algorithm. The proposed method is evaluated on multiple datasets and benchmarked against traditional single-bit and multi-bit binarization techniques. Moreover, we extend this analogy to continual feature binarization.

• Paul, Clarke; Cmelo, Ivan; Helin, Runar; Shende, Mayur Kishor; Granmo, Ole-Christoffer & Fayne, Darren (2026). The Tsetlin Machine: A “Third Way” in QSAR Modeling. Journal of Chemical Information and Modeling. ISSN 1549-9596. 66(11), s. 6250–6270. doi: 10.1021/acs.jcim.5c03109. Fulltekst i vitenarkiv Vis sammendrag

  Advances in Quantitative Structure Activity Relationship (QSAR) are led by two core paradigms, (1) descriptor engineering, where complex fixed-length vectors of compounds are generated and conventional ML methods are applied to those representations and (2) graphical chemical inputs (e.g., Simplified Molecular Input Line Entry System (SMILES), 2D-graph) being provided to deep learning neural network (NN) models, which construct their own internal representations of molecules and learn iteratively over them. Here we present the Tsetlin Machine (TM)─which combines the accuracy and easy-use of existing rule-based QSAR ML methods (e.g., RF and XGBoost), the iterative learning aspect of NN algorithms and its intrinsic interpretability. The TM uses teams of finite-state automata which capture frequent patterns as propositional logic (clauses) via reinforcement learning. The benchmarking pipeline presented here demonstrates that TM-QSAR coupled with ECFP4 descriptors frequently performs better than existing rule-based QSAR methods for ROC-AUC, PRC-AUC and PPV, with a high capacity for interscaffold generalization. However, due to the binary nature of TM-QSAR, performance it is currently limited when descretised continuous descriptors are used. TM-QSAR demonstrated particularly impressive classification scores for MOR (ROC-AUC = 0.87, PRC-AUC = 0.77) and CYPA4 (ROC-AUC = 0.92, PRC-AUC = 0.63), when compared to RF and XGBoost. Using TM in combination with substructural fingerprinting descriptors allows for an interpretability suite which can be extracted directly from clauses. Here we detail molecule property maps (TM-MPM) to view atom-wise TM-QSAR bioactivity contributions for single molecules and closed-form WAC scores (Weights × Activations × Clauses) for descriptor-wise contributions to regions of predicted chemical space. These methods show strong alignment of TM-QSAR interpretations to known ligand–protein interactions of the MOR target and gives nonlinear, conditional interpretations for greater predicted bioactivity. Given this combination of accuracy, computational efficiency and interpretability, we provide a basis for TM-QSAR to be explored as a standard methodology in virtual screening toolkits.

• Halenka, Vojtech; Amini, Mohammadreza; Andersen, Per-Arne; Granmo, Ole-Christoffer; Jiao, Lei & Kantarci, Burak (2026). Analyzing Backdoor Vulnerabilities in Interpretable Machine Learning for Wireless Jamming Detection Using Tsetlin Machines. IEEE Transactions on Network Science and Engineering (IEEE TNSE). 13, s. 11869–11886. doi: 10.1109/TNSE.2026.3727545. Fulltekst i vitenarkiv Vis sammendrag

  Interpretable machine learning is increasingly sought in next-generation cellular networks, where trust, accountability, and robustness are essential and jamming remains a persistent threat. Federated learning enables collaborative jamming detection without sharing raw in-phase and quadrature data, while Tsetlin Machines provide a logic-based option for transparent, resource-constrained deployments. However, the security implications of interpretability in federated wireless environments remain poorly understood. We introduce a backdoor threat model for interpretable federated jamming detectors, showing how Tsetlin Machine clause structure can be exploited by a compromised client to induce targeted detection failures. In a federated framework with weighted Coalesced Tsetlin Machines and Krum aggregation, we analyze clause-based vulnerability to spectrogram-domain trigger perturbations and formulate a multi-objective problem balancing trigger effectiveness, model deviation, and aggregation selection. We further show that clause-informed trigger initialization lowers adversarial optimization effort, revealing a tension between transparency and robustness. Evaluation on 60,000 spectrograms from a 5G NR synchronization-signal testbed shows that optimized triggers can exceed 70% trial-level triggered false-negative rates in optimizer benchmarks, reaching approximately 90% in best-case configurations; supplemental multi-round federated evaluation shows that trial-level and global triggered false-negative rate (TFR) can diverge substantially (gaps from -31.4 to +3.0 percentage points across evaluated partitions), with no sustained global TFR≥70% after the last malicious selection round. These results highlight the need for defense-aware design of explainable models in next-generation networks.

• Shivakumar, Thrishank Hesaraghatta; Bethi, Pardhasaradhi; Boppu, Srinivas; Granmo, Ole-Christoffer & Cenkeramaddi, Linga Reddy (2026). Multi-Sensor Fusion using Composite Tsetlin Machine with Adaptive Feature Bank Selection. IEEE Sensors Journal. ISSN 1530-437X. 26(11), s. 17210–17223. doi: 10.1109/JSEN.2026.3680022. Fulltekst i vitenarkiv Vis sammendrag

  A wide range of applications relies on multisensor setups to enhance their perception and decision-making capabilities. These sensors generate raw time-series data that can be transformed into the frequency domain using feature banks such as mel frequency cepstral coefficients (MFCC), Chroma-STFT (C-STFT), and spectral descriptors. Most deep learning (DL) and machine learning (ML) models utilize these frequency-domain representations, typically in the form of numeric data or spectrogram images, to enhance their decision-making capabilities. However, interpretability, resource constraints, and inference time remain challenging in DL and ML algorithms. The Tsetlin machine (TM) is an energy-efficient alternative based on propositional logic. TM applications to multisensor classification and fusion remain largely unexplored. In this work, a novel multisensor fusion framework using composite-TM (Co-TM) is proposed, where each sensor’s time-series signals are converted into frequency-domain representations using several feature banks. The framework adaptively selects the best frequency-domain representation during the feature bank selection phase and performs sensor-level fusion during training. The feature bank selection is guided by the TM’s learning and delearning behaviors, while sensor-level fusion is achieved through a Co-TM framework. To monitor TM learning dynamics and adaptively select the desired feature bank for each sensor, we propose a set of metrics, including average accuracy, top-m accuracy, stability coefficient, and the slope of the accuracy curve. The proposed framework is validated using an industrial machine fault detection dataset (multisensor heterogeneous data) and a rotating machinery fault dataset (multisensor homogeneous data). The experimental results demonstrate that the proposed method achieves state-ofthe- art accuracy compared with ML, convolutional neural network (CNN) models, and TM models.

• Gadari, Charitha; Yeduri, Sreenivasa Reddy; Granmo, Ole-Christoffer & Cenkeramaddi, Linga Reddy (2026). Human Activity Recognition Using 5G RF Sensing and Interpretable Tsetlin Machines. Communication Systems and Networks and Workshops. Proceedings. ISSN 2155-2487. s. 953–958. doi: 10.1109/COMSNETS67989.2026.11418257. Fulltekst i vitenarkiv
• Salvi, Bhumika; Yeduri, Sreenivasa Reddy; Granmo, Ole-Christoffer & Cenkeramaddi, Linga Reddy (2026). Tsetlin Machine-based Network Anomaly Detection System. Communication Systems and Networks and Workshops. Proceedings. ISSN 2155-2487. s. 67–74. doi: 10.1109/COMSNETS67989.2026.11418184. Fulltekst i vitenarkiv
• Kadhim, Ahmed Khalid; Lei, Jiao; Shafik, Rishad Ahmed; Granmo, Ole-Christoffer & Bhattarai, Bimal (2025). Scalable Multi-phase Word Embedding Using Conjunctive Propositional Clauses. I Lei, Jiao & Shafik, Rishad Ahmed (Red.), Tsetlin Machine (ISTM), International Symposium on the. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798331569228. doi: 10.1109/istm67926.2025.00024. Fulltekst i vitenarkiv
• Tunheim, Svein Anders; Zheng, Yujin; Jiao, Lei; Shafik, Rishad; Yakovlev, Alex & Granmo, Ole-Christoffer (2025). An All-Digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification Accelerator. IEEE Transactions on Circuits and Systems I: Regular Papers. ISSN 1549-8328. 73(2), s. 1107–1120. doi: 10.1109/TCSI.2025.3586698. Fulltekst i vitenarkiv Vis sammendrag

  We present an all-digital programmable machine learning accelerator chip for image classification, underpinning on the Tsetlin machine (TM) principles. The TM is an emerging machine learning algorithm founded on propositional logic, utilizing sub-pattern recognition expressions called clauses. The accelerator implements the coalesced TM version with convolution, and classifies booleanized images of 28×28 pixels with 10 categories. A configuration with 128 clauses is used in a highly parallel architecture. Fast clause evaluation is achieved by keeping all clause weights and Tsetlin automata (TA) action signals in registers. The chip is implemented in a 65 nm low-leakage CMOS technology, and occupies an active area of 2.7 mm2. At a clock frequency of 27.8 MHz, the accelerator achieves 60.3 k classifications per second, and consumes 8.6 nJ per classification. This demonstrates the energy-efficiency of the TM, which was the main motivation for developing this chip. The latency for classifying a single image is 25.4 μ s which includes system timing overhead. The accelerator achieves 97.42%, 84.54% and 82.55% test accuracies for the datasets MNIST, Fashion-MNIST and Kuzushiji-MNIST, respectively, matching the TM software models.

• Tarasyuk, Olga; Gorbenko, Anatoliy; Rahman, Tousif; Jiao, Lei; Granmo, Ole-Christoffer & Shafik, Rishad [Vis alle 7 forfattere av denne artikkelen] (2025). Learning dynamics, pattern recognition capability and interpretability of the Tsetlin Machine. Pattern Recognition. ISSN 0031-3203. 174. doi: 10.1016/j.patcog.2025.113028. Fulltekst i vitenarkiv Vis sammendrag

  The inability to trace an AI’s reasoning process and understand why it makes each decision is known as the black box problem. This remains one of the major barriers to the trusted and widespread use of machine learning in many application domains. The paper explores pattern recognition performance and learning dynamics of the Tsetlin Machine – a new explainable logic-based machine-learning approach. Tsetlin Machine uses a collection of finite-state automata with a unique logic-based learning mechanism and provides a promising alternative to Artificial Neural Networks with several advantages, such as interpretability, low complexity, suitability for hardware implementation and high performance. This work investigates Tsetlin Machine’s mechanism for constructing conjunctive clauses from data and their interpretation for pattern recognition on several datasets. We demonstrate that during training the logical clauses learn persistent sub-patterns within the class. Each clause creates a class template by clustering a certain number of similar class samples, combining them through literal-wise logical conjunction (i.e., AND-ing). The number of class samples that each clause combines depends on Tsetlin Machine’s hyperparameters. The more class samples that are combined, the more general the clauses become. The paper aims at uncovering how Tsetlin Machine’s hyperparameters influence the balance between clause generalization and specialization and how this affects the accuracy of pattern recognition. It also studies the evolution of the machine’s internal state, its convergence and training completion.

• Jeeru, Sindhusha; Omslandseter, Rebekka Olsson; Andersen, Per-Arne; Morrison, Aiden James; Sokolova, Nadezda & Granmo, Ole-Christoffer [Vis alle 7 forfattere av denne artikkelen] (2025). MixCTME: A Mixture of Convolutional Tsetlin Machine Experts Using Diverse Spectrogram Visualizations for Jamming Signal Classification. IEEE Internet of Things Journal. ISSN 2327-4662. 12(22), s. 47667–47678. doi: 10.1109/jiot.2025.3606366. Fulltekst i vitenarkiv Vis sammendrag

  global navigation satellite systems (GNSSs) are vulnerable to jamming, which can degrade or even disable their services by interfering with signal reception. Such interference may interrupt GNSS positioning, navigation, timing, and communication functions. Therefore, robust jamming detection strategies are essential to ensure continuous and reliable services. Many existing jamming detection approaches use closed box machine learning (ML) models, which lack transparency and accuracy. In this article, we propose a novel mixture of convolutional Tsetlin machine experts (MixCTME) approach, using diverse spectrogram visualizations to enhance the accuracy and interpretability of jamming signal classification. To facilitate this, we collected raw in-phase and quadrature (IQ) data and named it the RealRFI dataset, which corresponds to ten different jamming classes. The data were collected through multiple radio-frequency interference (RFI) monitoring stations deployed at SINTEF companies across Europe and Scandinavia. Next, diverse visualizations were generated using short time Fourier transform (STFT), dominant frequency, fast Fourier transform (FFT), power spectral density, and standard deviation. These visualizations were binarized using the Otsu thresholding technique, and the binarized spectrograms were fed to the MixCTME model. Our method utilizes a combination of distinct convolutional Tsetlin machine (CTM) experts and employs a novel nonlinear technique, referred to as confidence-based gating, for weighting the experts’ inputs to make the final decision. We compared our method against state-of-the-art approaches via the self-collected and labeled dataset. Through experiments, our model achieved an accuracy of 90.70% on the collected data and 99.46% on a benchmark dataset, outperforming the state-of-the-art approaches. Additionally, we highlight the trustworthiness, scalability, and interpretability of the proposed approach, presenting a promising solution for accurate and interpretable jamming classification.

• Belaid, Mohamed-Bachir; Sharma, Jivitesh; Lei, Jiao; Granmo, Ole-Christoffer; Andersen, Per-Arne & Yazidi, Anis (2025). Generalized Convergence Analysis of Tsetlin Automaton Based Algorithms: A Probabilistic Approach to Concept Learning. I Walsh, Toby; Shah, Julie & Kolter, Zico (Red.), Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence. AAAI Press. ISSN 9781577358978. s. 15524–15531. doi: 10.1609/aaai.v39i15.33704. Fulltekst i vitenarkiv
• Jeeru, Sindhusha; Lei, Jiao; Andersen, Per-Arne & Granmo, Ole-Christoffer (2025). Interpretable Rule-based Architecture for GNSS Jamming Signal Classification. IEEE Sensors Journal. ISSN 1530-437X. 25(10), s. 17942–17959. doi: 10.1109/JSEN.2025.3558966. Fulltekst i vitenarkiv Vis sammendrag

  Jamming is a fatal threat to a global navigation satellite system (GNSS), and an efficient anti-jamming system relies on successful classification and identification of jamming types to respond effectively. The existing solutions suffer either from poor accuracy or lack of interpretability, and they are prone to learning simple statistical correlations rather than more fundamental and general relationships. In this study, we propose a novel approach to classify GNSS jamming signals as intentional or unintentional. The approach introduces a new standard deviation-based denoising method, which makes it possible to use the logical rule-based architecture of the convolutional Tsetlin machine (CTM) for interpretable jamming signal analysis. CTM is a recently developed algorithm that solves complex classification problems using conjunctive propositional formulas through a team of Tsetlin automata (TA). Unlike traditional opaque models based on deep learning, our approach goes beyond classification and provides a human-level interpretation of features. This interpretation capability allows a deeper comprehension of the characteristics and underlying patterns of the jamming signals, significantly easing the decision-making process. Furthermore, the CTM approach is also evaluated with different Booleanization techniques. Through experiments, we show that the proposed approach with CTM achieves an F1-score of 98.7%, on the collected dataset, which is superior to the state-of-the-art.

• Kadhim, Ahmed Khalid; Granmo, Ole-Christoffer; Lei, Jiao & Shafik, Rishad Ahmed (2024). Exploring State Space and Reasoning by Elimination in Tsetlin Machines. I NN, NN (Red.), 2024 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798331504984. Fulltekst i vitenarkiv Vis sammendrag

  The Tsetlin Machine (TM) has gained significant attention in Machine Learning (ML). By employing logical fundamentals, it facilitates pattern learning and representation, offering an alternative approach for developing comprehensible Artificial Intelligence (AI) with a specific focus on pattern classification in the form of conjunctive clauses. In the domain of Natural Language Processing (NLP), TM is utilised to construct word embedding and describe target words using clauses. To enhance the descriptive capacity of these clauses, we study the concept of Reasoning by Elimination (RbE) in clauses' formulation, which involves incorporating feature negations to provide a more comprehensive representation. In more detail, this paper employs the Tsetlin Machine Auto-Encoder (TM-AE) architecture to generate dense word vectors, aiming at capturing contextual information by extracting feature-dense vectors for a given vocabulary. Thereafter, the principle of RbE is explored to improve descriptivity and optimise the performance of the TM. Specifically, the specificity parameter <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$s$</tex> and the voting margin parameter <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$T$</tex> are leveraged to regulate feature distribution in the state space, resulting in a dense representation of information for each clause. In addition, we investigate the state spaces of TM-AE, especially for the forgotten/excluded features. Empirical investigations on artificially generated data, the IMDB dataset, and the 20 Newsgroups dataset showcase the robustness of the TM, with accuracy reaching 90.62% for the IMDB.

• Biermann, Daniel; Palumbo, Fabrizio; Goodwin, Morten & Granmo, Ole-Christoffer (2024). Streamlining Attention for Text Classification: Sequence Length Reduction with Pooling Attention. I Bramer, Max & Stahl, Frederic (Red.), Artificial Intelligence XLI: 44th SGAI International Conference on Artificial Intelligence, AI 2024. Springer. ISSN 9783031779145. s. 61–73. doi: 10.1007/978-3-031-77915-2_5. Fulltekst i vitenarkiv
• Tunheim, Svein Anders; Lei, Jiao; Shafik, Rishad; Yakovlev, Alex & Granmo, Ole-Christoffer (2024). Tsetlin Machine-Based Image Classification FPGA Accelerator With On-Device Training. IEEE Transactions on Circuits and Systems I: Regular Papers. ISSN 1549-8328. 72(2), s. 830–843. doi: 10.1109/TCSI.2024.3519191. Fulltekst i vitenarkiv
• Andersen, Per-Arne; Goodwin, Morten & Granmo, Ole-Christoffer (2024). Towards safe and sustainable reinforcement learning for real-time strategy games. Information Sciences. ISSN 0020-0255. 679. doi: 10.1016/j.ins.2024.120980. Fulltekst i vitenarkiv
• Abouzeid, Ahmed Abdulrahem Othman; Granmo, Ole-Christoffer; Goodwin, Morten & Webersik, Christian (2024). Towards misinformation mitigation on social media: novel user activity representation for modeling societal acceptance. Journal of Computational Social Science (JCSS). ISSN 2432-2717. doi: 10.1007/s42001-024-00256-9. Fulltekst i vitenarkiv
• Halenka, Vojtech; Kadhim, Ahmed Khalid; Paul, Clarke; Bhattarai, Bimal; Saha, Rupsa & Granmo, Ole-Christoffer [Vis alle 8 forfattere av denne artikkelen] (2024). Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines. I NN, NN (Red.), 2024 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798331504984. doi: 10.1109/ISTM62799.2024.10931546. Fulltekst i vitenarkiv Vis sammendrag

  Tsetlin machines (TMs) have been successful in several application domains, operating with high efficiency on Boolean representations of the input data. However, Booleanizing complex data structures such as sequences, graphs, images, signal spectra, chemical compounds, and natural language is non-trivial. In this paper, we propose a hypervector (HV) based method for expressing arbitrarily large sets of concepts associated with any input data. Using a hyperdimensional space to build vectors drastically expands the capacity and flexibility of the TM. We demonstrate how images, chemical compounds, and natural language text are encoded according to the proposed method, and how the resulting HV -powered TM can achieve significantly higher accuracy and faster learning on well-known benchmarks. Our results thus open up a new research direction for TMs, namely how to expand and exploit the benefits of operating in hyperspace, including new booleanization strategies, optimization of TM inference and learning, as well as new TM applications.

• Bhattarai, Bimal; Granmo, Ole-Christoffer; Jiao, Lei; Yadav, Rohan Kumar & Sharma, Jivitesh (2024). Tsetlin Machine Embedding: Representing Words Using Logical Expressions, Findings of the Association for Computational Linguistics: EACL 2024. Association for Computational Linguistics (ACL). ISSN 9798891760936. s. 1512–1520. Fulltekst i vitenarkiv
• Maheshwari, Sidharth; Rahman, Tousif; Shafik, Rishad; Yakovlev, Alex; Rafiev, Ashur & Lei, Jiao [Vis alle 7 forfattere av denne artikkelen] (2023). REDRESS: Generating Compressed Models for Edge Inference Using Tsetlin Machines. IEEE Transactions on Pattern Analysis and Machine Intelligence. ISSN 0162-8828. 45(9), s. 11152–11168. doi: 10.1109/TPAMI.2023.3268415. Fulltekst i vitenarkiv Vis sammendrag

  Inference at-the-edge using embedded machine learning models is associated with challenging trade-offs between resource metrics, such as energy and memory footprint, and the performance metrics, such as computation time and accuracy. In this work, we go beyond the conventional Neural Network based approaches to explore Tsetlin Machine (TM), an emerging machine learning algorithm, that uses learning automata to create propositional logic for classification. We use algorithm-hardware co-design to propose a novel methodology for training and inference of TM. The methodology, called REDRESS, comprises independent TM training and inference techniques to reduce the memory footprint of the resulting automata to target low and ultra-low power applications. The array of Tsetlin Automata (TA) holds learned information in the binary form as bits: {0,1} , called excludes and includes, respectively. REDRESS proposes a lossless TA compression method, called the include-encoding, that stores only the information associated with includes to achieve over 99% compression. This is enabled by a novel computationally minimal training procedure, called the Tsetlin Automata Re-profiling, to improve the accuracy and increase the sparsity of TA to reduce the number of includes, hence, the memory footprint. Finally, REDRESS includes an inherently bit-parallel inference algorithm that operates on the optimally trained TA in the compressed domain, that does not require decompression during runtime, to obtain high speedups when compared with the state-of-the-art Binary Neural Network (BNN) models. In this work, we demonstrate that using REDRESS approach, TM outperforms BNN models on all design metrics for five benchmark datasets viz. MNIST, CIFAR2, KWS6, Fashion-MNIST and Kuzushiji-MNIST. When implemented on an STM32F746G-DISCO microcontroller, REDRESS obtained speedups and energy savings ranging 5-5700× compared with different BNN models.

• Biermann, Daniel; Goodwin, Morten & Granmo, Ole-Christoffer (2023). Knowledge Infused Representations Through Combination of Expert Knowledge and Original Input. I Zouganeli, Evi; Yazidi, Anis; Mello, Gustavo Borges Moreno e & Lind, Pedro (Red.), Nordic Artificial Intelligence Research and Development: 4th Symposium of the Norwegian AI Society, NAIS 2022, Oslo, Norway, May 31-June 1, 2022, Revised Selected Papers. Springer Nature. ISSN 9783031170294. s. 3–15. doi: 10.1007/978-3-031-17030-0_1. Fulltekst i vitenarkiv Vis sammendrag

  Sophisticated applications in natural language processing, such as conversational agents, often need to be able to generalize across a range of different tasks to generate natural-feeling language. In this paper, we introduce a model that aims to improve generalizability with regard to different tasks by combining the original input with the output of a task-specific expert. Through a combination mechanism, we create a new representation that has been enriched with the information given by the expert. These enriched representations then serve as input to a downstream model. We test three different combination mechanisms in two combination paradigms and evaluate the performance of the new enriched representation in a simple encoder-decoder model. We show that even very simple combination mechanisms are able to significantly improve performance of the downstream model. This means that the encoded expert information is transported through the new enriched input representation, leading to a beneficial impact on performance within the task domain. This opens the way for exciting future endeavors such as testing performance on different task domains and the combination of multiple experts.

• Sharma, Jivitesh; Yadav, Rohan Kumar; Granmo, Ole-Christoffer & Lei, Jiao (2023). Drop Clause: Enhancing Performance, Robustness and Pattern Recognition Capabilities of the Tsetlin Machine. I Chen, Yiling & Neville, Jennifer (Red.), Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence. AAAI Press. ISSN 9781577358800. s. 13547–13555. doi: 10.1609/aaai.v37i11.26588. Fulltekst i vitenarkiv
• Bhattarai, Bimal; Granmo, Ole-Christoffer & Lei, Jiao (2023). An Interpretable Knowledge Representation Framework for Natural Language Processing with Cross-Domain Application, Advances in Information Retrieval. ECIR 2023. Springer. ISSN 9783031282447. s. 167–181. doi: 10.1007/978-3-031-28244-7_11. Fulltekst i vitenarkiv Vis sammendrag

  Data representation plays a crucial role in natural language processing (NLP), forming the foundation for most NLP tasks. Indeed, NLP performance highly depends upon the effectiveness of the preprocessing pipeline that builds the data representation. Many representation learning frameworks, such as Word2Vec, encode input data based on local contextual information that interconnects words. Such approaches can be computationally intensive, and their encoding is hard to explain. We here propose an interpretable representation learning framework utilizing Tsetlin Machine (TM). The TM is an interpretable logic-based algorithm that has exhibited competitive performance in numerous NLP tasks. We employ the TM clauses to build a sparse propositional (boolean) representation of natural language text. Each clause is a class-specific propositional rule that links words semantically and contextually. Through visualization, we illustrate how the resulting data representation provides semantically more distinct features, better separating the underlying classes. As a result, the following classification task becomes less demanding, benefiting simple machine learning classifiers such as Support Vector Machine (SVM). We evaluate our approach using six NLP classification tasks and twelve domain adaptation tasks. Our main finding is that the accuracy of our proposed technique significantly outperforms the vanilla TM, approaching the competitive accuracy of deep neural network (DNN) baselines. Furthermore, we present a case study showing how the representations derived from our framework are interpretable. (We use an asynchronous and parallel version of Tsetlin Machine: available at https://github.com/cair/PyTsetlinMachineCUDA).

• Tunheim, Svein Anders; Lei, Jiao; Shafik, Rishad Ahmed; Yakovlev, Alexandre & Granmo, Ole-Christoffer (2023). Convolutional Tsetlin Machine-based Training and Inference Accelerator for 2-D Pattern Classification. Microprocessors and Microsystems: Embedded Hardware Design (MICPRO). ISSN 0141-9331. 103. doi: 10.1016/j.micpro.2023.104949. Fulltekst i vitenarkiv Vis sammendrag

  The Tsetlin Machine (TM) is a machine learning algorithm based on an ensemble of Tsetlin Automata (TAs) that learns propositional logic expressions from Boolean input features. In this paper, the design and implementation of a Field Programmable Gate Array (FPGA) accelerator based on the Convolutional Tsetlin Machine (CTM) is presented. The accelerator performs classification of two pattern classes in 4 × 4 Boolean images with a 2 × 2 convolution window. Specifically, there are two separate TMs, one per class. Each TM comprises 40 propositional logic formulas, denoted as clauses, which are conjunctions of literals. Include/exclude actions from the TAs determine which literals are included in each clause. The accelerator supports full training, including random patch selection during convolution based on parallel reservoir sampling across all clauses. The design is implemented on a Xilinx Zynq XC7Z020 FPGA platform. With an operating clock speed of 40 MHz, the accelerator achieves a classification rate of 4.4 million images per second with an energy per classification of 0.6 J. The mean test accuracy is 99.9% when trained on the 2-dimensional Noisy XOR dataset with 40% noise in the training labels. To achieve this performance, which is on par with the original software implementation, Linear Feedback Shift Register (LFSR) random number generators of minimum 16 bits are required. The solution demonstrates the core principles of a CTM and can be scaled to operate on multi-class systems for larger images.

• Tunheim, Svein Anders; Lei, Jiao & Granmo, Ole-Christoffer (2023). Model Export for the Convolutional Coalesced Tsetlin Machine, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10455048. Fulltekst i vitenarkiv
• Przybysz, Emilia Katarzyna; Bhattarai, Bimal; Persia, Cosimo Damiano; Ozaki, Ana; Granmo, Ole-Christoffer & Sharma, Jivitesh (2023). Verifying Properties of Tsetlin Machines, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10454997. Fulltekst i vitenarkiv
• Granmo, Ole-Christoffer; Andersen, Per-Arne; Lei, Jiao; Zhang, Xuan; Blakely, Christian Dallas & Berge, Geir Thore [Vis alle 7 forfattere av denne artikkelen] (2023). Learning Minimalistic Tsetlin Machine Clauses with Markov Boundary-Guided Pruning, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10454914. Fulltekst i vitenarkiv
• Gorji, Saeed Rahimi; Granmo, Ole-Christoffer & Goodwin, Morten (2023). Natural Language Modeling with the Tsetlin Machine. I Fujita, H. (Red.), Advances and Trends in Artificial Intelligence. Theory and Applications. IEA/AIE 2023.. Springer. ISSN 9783031368219. s. 141–150. doi: 10.1007/978-3-031-36822-6_12. Fulltekst i vitenarkiv
• Abeyrathna, Kuruge Darshana; Mekkaoui, Sara El; Edward, L. Yi; Hafver, Andreas & Granmo, Ole-Christoffer (2023). Extension of Regression Tsetlin Machine for Interpretable Uncertainty Assessment. I Fensel, Anna; Ozaki, Ana; Dumitru, Roman & Soylu, Ahmet (Red.), Rules and Reasoning - 7th International Joint Conference, RuleML+RR 2023, Oslo, Norway, September 18-20, 2023, Proceedings. Springer Publishing Company. ISSN 9783031450716. s. 19–33. doi: 10.1007/978-3-031-45072-3_2. Fulltekst i vitenarkiv
• Biermann, Daniel; Goodwin, Morten & Granmo, Ole-Christoffer (2023). Transfer Learning Through Knowledge-Infused Representations with Contextual Experts. I Maglogiannis, Ilias; Iliadis, L.; MacIntyre, J. & Dominguez, Manuel (Red.), Artificial Intelligence Applications and Innovations. Springer. ISSN 9783031341069. doi: 10.1007/978-3-031-34107-6_45. Fulltekst i vitenarkiv
• Bhattarai, Bimal; Saha, Rupsa; Granmo, Ole-Christoffer; Zadorozhny, Vladimir & Xu, Jiawei (2023). A Logic-Based Explainable Framework for Relation Classification of Human Rights Violations. CEUR Workshop Proceedings. 3464, s. 14–21. Fulltekst i vitenarkiv Vis sammendrag

  Using a Relational Tsetlin Machine (RTM) for analysis of semi-structured data allows the use of inherent relational structures present in natural language text to get an explainable classification of data. A finite Herbrand model derives Horn Clauses from the model, which are simple yet powerful logical tools that can build an abstract view of the world. We use the same to analyze human rights violation data. We show concretely how natural language can be transformed into a relational structure, and further use the Relational Tsetlin Machine to not only classify incidents as serious and non-serious violations but also explore the patterns learned by the RTM in order to arrive that those decisions. Furthermore, the distilled Horn Clauses show a precise understanding of the concepts involved without the drawback of textual ambiguity.

• Abeyrathna, Kuruge Darshana; Abouzeid, Ahmed Abdulrahem Othman; Bhattarai, Bimal; Giri, Charul; Glimsdal, Sondre & Granmo, Ole-Christoffer [Vis alle 11 forfattere av denne artikkelen] (2023). Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size. I Elkind, Edith (Red.), Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. AAAI Press. ISSN 9781956792034. s. 3395–3403. doi: 10.24963/ijcai.2023/378. Fulltekst i vitenarkiv Vis sammendrag

  Tsetlin machine (TM) is a logic-based machine learning approach with the crucial advantages of being transparent and hardware-friendly. While TMs match or surpass deep learning accuracy for an increasing number of applications, large clause pools tend to produce clauses with many literals (long clauses). As such, they become less interpretable. Further, longer clauses increase the switching activity of the clause logic in hardware, consuming more power. This paper introduces a novel variant of TM learning – Clause Size Constrained TMs (CSC-TMs) – where one can set a soft constraint on the clause size. As soon as a clause includes more literals than the constraint allows, it starts expelling literals. Accordingly, oversized clauses only appear transiently. To evaluate CSC-TM, we conduct classifcation, clustering, and regression experiments on tabular data, natural language text, images, and board games. Our results show that CSC-TM maintains accuracy with up to 80 times fewer literals. Indeed, the accuracy increases with shorter clauses for TREC, IMDb, and BBC Sports. After the accuracy peaks, it drops gracefully as the clause size approaches a single literal. We fnally analyze CSC-TM power consumption and derive new convergence properties.

• Berge, Geir Thore; Granmo, Ole-Christoffer; Tveit, Tor Oddbjørn; Ruthjersen, Anna Linda & Sharma, Jivitesh (2023). Combining unsupervised, supervised and rule-based learning: the case of detecting patient allergies in electronic health records. BMC Medical Informatics and Decision Making. 23. doi: 10.1186/s12911-023-02271-8. Fulltekst i vitenarkiv Vis sammendrag

  Background Data mining of electronic health records (EHRs) has a huge potential for improving clinical decision support and to help healthcare deliver precision medicine. Unfortunately, the rule-based and machine learning-based approaches used for natural language processing (NLP) in healthcare today all struggle with various shortcomings related to performance, efciency, or transparency. Methods In this paper, we address these issues by presenting a novel method for NLP that implements unsupervised learning of word embeddings, semi-supervised learning for simplifed and accelerated clinical vocabulary and concept building, and deterministic rules for fne-grained control of information extraction. The clinical language is automatically learnt, and vocabulary, concepts, and rules supporting a variety of NLP downstream tasks can further be built with only minimal manual feature engineering and tagging required from clinical experts. Together, these steps create an open processing pipeline that gradually refnes the data in a transparent way, which greatly improves the interpretable nature of our method. Data transformations are thus made transparent and predictions interpretable, which is imperative for healthcare. The combined method also has other advantages, like potentially being language independent, demanding few domain resources for maintenance, and able to cover misspellings, abbreviations, and acronyms. To test and evaluate the combined method, we have developed a clinical decision support system (CDSS) named Information System for Clinical Concept Searching (ICCS) that implements the method for clinical concept tagging, extraction, and classifcation. Results In empirical studies the method shows high performance (recall 92.6%, precision 88.8%, F-measure 90.7%), and has demonstrated its value to clinical practice. Here we employ a real-life EHR-derived dataset to evaluate the method’s performance on the task of classifcation (i.e., detecting patient allergies) against a range of common supervised learning algorithms. The combined method achieves state-of-the-art performance compared to the alternative methods we evaluate. We also perform a qualitative analysis of common word embedding methods on the task of word similarity to examine their potential for supporting automatic feature engineering for clinical NLP tasks. Conclusions Based on the promising results, we suggest more research should be aimed at exploiting the inherent synergies between unsupervised, supervised, and rule-based paradigms for clinical NLP.

• Bhattarai, Bimal; Granmo, Ole-Christoffer; Lei, Jiao; Andersen, Per-Arne; Tunheim, Svein Anders & Shafik, Rishad Ahmed [Vis alle 7 forfattere av denne artikkelen] (2023). Contracting Tsetlin Machine with Absorbing Automata, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10455040. Fulltekst i vitenarkiv
• Liland, Kristian Hovde; Tomic, Oliver; Indahl, Ulf Geir; Futsæther, Cecilia Marie; Lei, Jiao & Granmo, Ole-Christoffer [Vis alle 7 forfattere av denne artikkelen] (2023). Tsetlin Machine in DNA sequence classification : Application to prokaryote gene prediction / A match made in silico, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10454960. Fulltekst i vitenarkiv
• Sahu, Prajwal Kumar; Boppu, Srinivas; Shafik, Rishad Ahmed; Tunheim, Svein Anders; Granmo, Ole-Christoffer & Cenkeramaddi, Linga Reddy (2023). Enhancing Inference Performance through Include only Literal Incorporation in Tsetlin Machine, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10455016. Fulltekst i vitenarkiv
• Drøsdal, Didrik Kallhovd; Grimsmo, Andreas; Andersen, Per-Arne; Granmo, Ole-Christoffer & Goodwin, Morten (2023). Exploring the Potential of Model-Free Reinforcement Learning using Tsetlin Machines, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10455080. Fulltekst i vitenarkiv
• Tarasyuk, Olga; Rahman, Tousif; Shafik, Rishad Ahmed; Yakovlev, Alexandre; Gorbenko, Anatoliy & Granmo, Ole-Christoffer [Vis alle 7 forfattere av denne artikkelen] (2023). Systematic Search for Optimal Hyper-parameters of the Tsetlin Machine on MNIST Dataset, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10454969. Fulltekst i vitenarkiv
• Gunvaldsen, Ole; Thorsen, Henning Blomfeld; Andersen, Per-Arne; Granmo, Ole-Christoffer & Goodwin, Morten (2023). Towards IoT Anomaly Detection with Tsetlin Machines, 2023 International Symposium on the Tsetlin Machine (ISTM). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350344776. doi: 10.1109/ISTM58889.2023.10455063. Fulltekst i vitenarkiv
• Berge, Geir Thore; Granmo, Ole-Christoffer; Tveit, Tor Oddbjørn; Munkvold, Bjørn Erik; Ruthjersen, Anna Linda & Sharma, Jivitesh (2023). Machine learning-driven clinical decision support system for concept-based searching: a field trial in a Norwegian hospital. BMC Medical Informatics and Decision Making. 23. doi: 10.1186/s12911-023-02101-x. Fulltekst i vitenarkiv Vis sammendrag

  Background Natural language processing (NLP) based clinical decision support systems (CDSSs) have demonstrated the ability to extract vital information from patient electronic health records (EHRs) to facilitate important decision support tasks. While obtaining accurate, medical domain interpretable results is crucial, it is demanding because realworld EHRs contain many inconsistencies and inaccuracies. Further, testing of such machine learning-based systems in clinical practice has received limited attention and are yet to be accepted by clinicians for regular use. Methods We present our results from the evaluation of an NLP-driven CDSS developed and implemented in a Norwegian Hospital. The system incorporates unsupervised and supervised machine learning combined with rulebased algorithms for clinical concept-based searching to identify and classify allergies of concern for anesthesia and intensive care. The system also implements a semi-supervised machine learning approach to automatically annotate medical concepts in the narrative. Results Evaluation of system adoption was performed by a mixed methods approach applying The Unifed Theory of Acceptance and Use of Technology (UTAUT) as a theoretical lens. Most of the respondents demonstrated a high degree of system acceptance and expressed a positive attitude towards the system in general and intention to use the system in the future. Increased detection of patient allergies, and thus improved quality of practice and patient safety during surgery or ICU stays, was perceived as the most important advantage of the system. Conclusions Our combined machine learning and rule-based approach benefts system performance, efciency, and interpretability. The results demonstrate that the proposed CDSS increases detection of patient allergies, and that the system received high-level acceptance by the clinicians using it. Useful recommendations for further system improvements and implementation initiatives are reducing the quantity of alarms, expansion of the system to include more clinical concepts, closer EHR system integration, and more workstations available at point of care.

• Gorji, Saeed Rahimi & Granmo, Ole-Christoffer (2023). Off-policy and on-policy reinforcement learning with the Tsetlin machine. Applied Intelligence - The International Journal of Research on Intelligent Systems for Real Life Complex Problems. ISSN 0924-669X. 53, s. 8596–8613. doi: 10.1007/s10489-022-04297-3. Fulltekst i vitenarkiv Vis sammendrag

  The Tsetlin Machine is a recent supervised learning algorithm that has obtained competitive accuracy- and resource usage results across several benchmarks. It has been used for convolution, classification, and regression, producing interpretable rules in propositional logic. In this paper, we introduce the first framework for reinforcement learning based on the Tsetlin Machine. Our framework integrates the value iteration algorithm with the regression Tsetlin Machine as the value function approximator. To obtain accurate off-policy state-value estimation, we propose a modified Tsetlin Machine feedback mechanism that adapts to the dynamic nature of value iteration. In particular, we show that the Tsetlin Machine is able to unlearn and recover from the misleading experiences that often occur at the beginning of training. A key challenge that we address is mapping the intrinsically continuous nature of state-value learning to the propositional Tsetlin Machine architecture, leveraging probabilistic updates. While accurate off-policy, this mechanism learns significantly slower than neural networks on-policy. However, by introducing multi-step temporal-difference learning in combination with high-frequency propositional logic patterns, we are able to close the performance gap. Several gridworld instances document that our framework can outperform comparable neural network models, despite being based on simple one-level AND-rules in propositional logic. Finally, we propose how the class of models learnt by our Tsetlin Machine for the gridworld problem can be translated into a more understandable graph structure. The graph structure captures the state-value function approximation and the corresponding policy found by the Tsetlin Machine.

• Tunheim, Svein Anders; Yadav, Rohan Kumar; Lei, Jiao; Shafik, Rishad & Granmo, Ole-Christoffer (2022). Cyclostationary Random Number Sequences for the Tsetlin Machine. I Fournier-Viger, Philippe; Fujita, Hamido; Ali, Moonis & Wang, Yinglin (Red.), Advances and Trends in Artificial Intelligence. Theory and Practices in Artificial Intelligence. 35th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2022, Kitakyushu, Japan, July 19–22, 2022, Proceedings. Springer. ISSN 9783031085291. s. 844–856. doi: 10.1007/978-3-031-08530-7_71. Fulltekst i vitenarkiv Vis sammendrag

  The Tsetlin Machine (TM) constitutes an emerging machine learning algorithm that has shown competitive performance on several benchmarks. The underlying concept of the TM is propositional logic determined by a group of finite state machines that learns patterns. Thus, TM-based systems naturally lend themselves to low-power operation when implemented in hardware for micro-edge Internet-of-Things applications. An important aspect of the learning phase of TMs is stochasticity. For low-power integrated circuit implementations the random number generation must be carried out efficiently. In this paper, we explore the application of pre-generated cyclostationary random number sequences for TMs. Through experiments on two machine learning problems, i.e., Binary Iris and Noisy XOR, we demonstrate that the accuracy is on par with standard TM. We show that through exploratory simulations the required length of the sequences that meets the conflicting tradeoffs can be suitably identified. Furthermore, the TMs achieve robust performance against reduced resolution of the random numbers. Finally, we show that maximum-length sequences implemented by linear feedback shift registers are suitable for generating the required random numbers.

• Jenul, Anna Selina; Bhattarai, Bimal; Liland, Kristian Hovde; Lei, Jiao; Schrunner, Stefan & Futsæther, Cecilia Marie [Vis alle 8 forfattere av denne artikkelen] (2022). Component Based Pre-filtering of Noisy Data for Improved Tsetlin Machine Modelling. I Shafik, Rishad (Red.), 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665471169. s. 57–64. doi: 10.1109/ISTM54910.2022.00019. Fulltekst i vitenarkiv Vis sammendrag

  Tabular data with few observations and many features are common in the healthcare domain. With its rule-based approach to data modelling, the Tsetlin Machine has considerable potential to be a valuable tool in healthcare data analysis by providing interpretability to medical personnel. However, the performance of Tsetlin Machine models may be hampered by the presence of noise, which may often be the case with healthcare data due to individual differences across patients. This study shows that intelligent pre-filtering of healthcare measurement data using so-called component-based methods, such as Principal Component Analysis or Partial Least Squares Regression, can be beneficial for the performance of Tsetlin Machines. Modelling four healthcare data sets shows that the Tsetlin Machine achieved better predictive performance on pre-filtered data for data sets with high features-to-observations ratios.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Lei, Jiao (2022). Explainable Tsetlin Machine Framework for Fake News Detection with Credibility Score Assessment. I Calzolari, Nicoletta; Béchet, Frédéric; Blache, Philippe; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Odijk, Jan & Piperidis, Stelios (Red.), Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association. ISSN 9791095546726. s. 4894–4903. Fulltekst i vitenarkiv Vis sammendrag

  The proliferation of fake news, i.e., news intentionally spread for misinformation, poses a threat to individuals and society. Despite various fact-checking websites such as PolitiFact, robust detection techniques are required to deal with the increase in fake news. Several deep learning models show promising results for fake news classification, however, their black-box nature makes it difficult to explain their classification decisions and quality-assure the models. We here address this problem by proposing a novel interpretable fake news detection framework based on the recently introduced Tsetlin Machine (TM). In brief, we utilize the conjunctive clauses of the TM to capture lexical and semantic properties of both true and fake news text. Further, we use clause ensembles to calculate the credibility of fake news. For evaluation, we conduct experiments on two publicly available datasets, PolitiFact and GossipCop, and demonstrate that the TM framework significantly outperforms previously published baselines by at least 5% in terms of accuracy, with the added benefit of an interpretable logic-based representation. In addition, our approach provides a higher F1-score than BERT and XLNet, however, we obtain slightly lower accuracy. We finally present a case study on our model’s explainability, demonstrating how it decomposes into meaningful words and their negations.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Lei, Jiao (2022). ConvTextTM: An Explainable Convolutional Tsetlin Machine Framework for Text Classification. I Calzolari, Nicoletta; Béchet, Frédéric; Blache, Philippe; Choukri, Khalid; Cieri, Christopher; Declerck, Thierry; Goggi, Sara; Isahara, Hitoshi; Maegaard, Bente; Mariani, Joseph; Mazo, Hélène; Odijk, Jan & Piperidis, Stelios (Red.), Proceedings of the Thirteenth Language Resources and Evaluation Conference. European Language Resources Association. ISSN 9791095546726. s. 3761–3770. Fulltekst i vitenarkiv Vis sammendrag

  Recent advancements in natural language processing (NLP) have reshaped the industry, with powerful language models such as GPT-3 achieving superhuman performance on various tasks. However, the increasing complexity of such models turns them into “black boxes”, creating uncertainty about their internal operation and decision-making. Tsetlin Machine (TM) employs human-interpretable conjunctive clauses in propositional logic to solve complex pattern recognition problems and has demonstrated competitive performance in various NLP tasks. In this paper, we propose ConvTextTM, a novel convolutional TM architecture for text classification. While legacy TM solutions treat the whole text as a corpus-specific set-of-words (SOW), ConvTextTM breaks down the text into a sequence of text fragments. The convolution over the text fragments opens up for local position-aware analysis. Further, ConvTextTM eliminates the dependency on a corpus-specific vocabulary. Instead, it employs a generic SOW formed by the tokenization scheme of the Bidirectional Encoder Representations from Transformers (BERT) (Devlin et al., 2019a). The convolution binds together the tokens, allowing ConvTextTM to address the out-of-vocabulary problem as well as spelling errors. We investigate the local explainability of our proposed method using clause-based features. Extensive experiments are conducted on seven datasets, to demonstrate that the accuracy of ConvTextTM is either superior or comparable to state-of-the-art baselines.

• Abouzeid, Ahmed Abdulrahem Othman; Granmo, Ole-Christoffer; Goodwin, Morten & Webersik, Christian (2022). Label-Critic Tsetlin Machine: A Novel Self-supervised Learning Scheme for Interpretable Clustering. I Shafik, Rishad (Red.), 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665471169. s. 41–48. doi: 10.1109/ISTM54910.2022.00016. Fulltekst i vitenarkiv Vis sammendrag

  Unlike typical machine learning algorithms such as Artificial Neural Networks, the Tsetlin Machine (TM) is based on propositional logic instead of arithmetic operations, promoting it as a novel machine learning paradigm with interpretable learning outcomes. To this end, this paper proposes a self-supervised learning scheme inspired by the self-correction and interpretability provided by a standard TM. The proposed architecture uses a twin of Label-Critic Tsetlin Automata (TAs). The Label-TA learns the individual samples’ correct labels guided by a self-corrected TM logical clause. At the same time, the Critic-TA validates the learning and approves the Label-TA reward. Our empirical results on synthetic and real data show promising capabilities for self-supervised learning and interpretable clustering. Furthermore, the Label-Critic TM architecture demonstrates how propositional logic-based learning provides self-correction with the absence of the ground truths in data.

• Abouzeid, Ahmed Abdulrahem Othman; Granmo, Ole-Christoffer; Webersik, Christian & Goodwin, Morten (2022). Socially Fair Mitigation of Misinformation on Social Networks via Constraint Stochastic Optimization. Proceedings of the AAAI Conference on Artificial Intelligence. ISSN 2159-5399. s. 11801–11809. doi: 10.1609/aaai.v36i11.21436. Fulltekst i vitenarkiv Vis sammendrag

  Recent social networks' misinformation mitigation approaches tend to investigate how to reduce misinformation by considering a whole-network statistical scale. However, unbalanced misinformation exposures among individuals urge to study fair allocation of mitigation resources. Moreover, the network has random dynamics which change over time. Therefore, we introduce a stochastic and non-stationary knapsack problem, and we apply its resolution to mitigate misinformation in social network campaigns. We further propose a generic misinformation mitigation algorithm that is robust to different social networks' misinformation statistics, allowing a promising impact in real-world scenarios. A novel loss function ensures fair mitigation among users. We achieve fairness by intelligently allocating a mitigation incentivization budget to the knapsack, and optimizing the loss function. To this end, a team of Learning Automata (LA) drives the budget allocation. Each LA is associated with a user and learns to minimize its exposure to misinformation by performing a non-stationary and stochastic walk over its state space. Our results show how our LA-based method is robust and outperforms similar misinformation mitigation methods in how the mitigation is fairly influencing the network users.

• Tunheim, Svein Anders; Lei, Jiao; Shafik, Rishad Ahmed; Yakovlev, Alexandre & Granmo, Ole-Christoffer (2022). A Convolutional Tsetlin Machine-based Field Programmable Gate Array Accelerator for Image Classification. I Shafik, Rishad (Red.), 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665471169. s. 21–28. doi: 10.1109/ISTM54910.2022.00013. Fulltekst i vitenarkiv Vis sammendrag

  This paper presents a Field Programmable Gate Array (FPGA) implementation of an image classification accelerator based on the Convolutional Tsetlin Machine (CTM). The work is a concept design, and the solution demonstrates recognition of two classes in 4 × 4 images with a 2 × 2 convolution window. More specifically, there are two sub-Tsetlin Machines (TMs), one per class. A single sub-TM employs 40 clauses, each controlled by 20 Tsetlin Automata. The accelerator features random patch selection, in parallel for all clauses, based on reservoir sampling. The design is implemented in a Xilinx Zync XC7Z020 FPGA. With an operating clock speed of 30 MHz, the accelerator is capable of inferring at the rate of 3.3 million images per second with an additional power consumption of 20 mW from idle mode. The average test accuracy is 96.7% when trained on data with 10% noise. A training session with 100 epochs and 8192 examples takes 1.5 seconds. Due to the limited hardware resources required, the CTM accelerator represents a promising concept for online learning in energy-frugal systems. The solution can be scaled to multi-class systems and larger images.

• Rafiev, Ashur; Morris, Jordan; Xia, Fei; Shafik, Rishad; Yakovlev, Alex & Granmo, Ole-Christoffer [Vis alle 7 forfattere av denne artikkelen] (2022). Visualization of Machine Learning Dynamics in Tsetlin Machines. I Shafik, Rishad (Red.), 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665471169. s. 65–72. doi: 10.1109/ISTM54910.2022.00020. Fulltekst i vitenarkiv Vis sammendrag

  The black-box approach towards machine learning models is not helpful for creating fast and efficient implementations. optimization of these models requires a clear understanding of every aspect of the system, including the architecture, algorithms, and dynamics of the training process. This paper presents a range of visualizations for investigating the dynamics of the Tsetlin Machine, which is a new machine-learning algorithm with logic underpinning. These include static visualizations such as architecture and algorithm diagrams and dynamic visualizations such as plotting the evolution of the internal state of the machine. The workflow that supports the visualizations is generalized into an extendable open-source development kit that can be used with future generations of Tsetlin Machines. The example visualization diagrams from the MNIST dataset are discussed from the viewpoint of parallel implementation, hardware acceleration, and opportunities for architectural optimization.

• Rahman, Tousif; Wheeldon, Adrian; Shafik, Rishad; Yakovlev, Alex; Lei, Jie & Granmo, Ole-Christoffer [Vis alle 7 forfattere av denne artikkelen] (2022). Data Booleanization for Energy Efficient On-Chip Learning using Logic Driven AI. I Shafik, Rishad (Red.), 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665471169. s. 29–36. doi: 10.1109/ISTM54910.2022.00014. Fulltekst i vitenarkiv Vis sammendrag

  The incorporation of Machine Learning (ML) models into smart devices and wearables has increased design focus on scalability and energy efficiency considerations. To transition towards on-device training, there must be a balance between data compaction to reduce ML complexity and data significance to maintain high learning efficacy. In this paper we examine a novel approach towards low-energy booleanization (i.e. Boolean encoding of raw data, which is different from binarization with positional significance used for encoding raw data) for a recently proposed machine learning method — the Tsetlin Machine. The approach in this paper offers a unique synergy between quantile binning for initial data encoding and logic minimization for significance-driven compaction of the dataset. Through this approach, the paper demonstrates how energy-frugal Tsetlin Machine models can be created with, for some datasets, up to 38.8x less energy consumption per datapoint during training. The proposed method offers significantly better energy efficiency with similar performance when compared with Binary Neural Network counterparts.

• Bhattarai, Bimal; Granmo, Ole-Christoffer & Lei, Jiao (2022). Word-level human interpretable scoring mechanism for novel text detection using Tsetlin Machines. Applied Intelligence - The International Journal of Research on Intelligent Systems for Real Life Complex Problems. ISSN 0924-669X. doi: 10.1007/s10489-022-03281-1. Fulltekst i vitenarkiv Vis sammendrag

  Recent research in novelty detection focuses mainly on document-level classification, employing deep neural networks (DNN). However, the black-box nature of DNNs makes it difficult to extract an exact explanation of why a document is considered novel. In addition, dealing with novelty at the word level is crucial to provide a more fine-grained analysis than what is available at the document level. In this work, we propose a Tsetlin Machine (TM)-based architecture for scoring individual words according to their contribution to novelty. Our approach encodes a description of the novel documents using the linguistic patterns captured by TM clauses. We then adapt this description to measure how much a word contributes to making documents novel. Our experimental results demonstrate how our approach breaks down novelty into interpretable phrases, successfully measuring novelty.

• Lei, Jiao; Zhang, Xuan; Granmo, Ole-Christoffer & Abeyrathna, Kuruge Darshana (2022). On the Convergence of Tsetlin Machines for the XOR Operator. IEEE Transactions on Pattern Analysis and Machine Intelligence. ISSN 0162-8828. 45(5), s. 6072–6085. doi: 10.1109/TPAMI.2022.3203150. Fulltekst i vitenarkiv Vis sammendrag

  The Tsetlin Machine (TM) is a novel machine learning algorithm with several distinct properties, including transparent inference and learning using hardware-near building blocks. Although numerous papers explore the TM empirically, many of its properties have not yet been analyzed mathematically. In this article, we analyze the convergence of the TM when input is non-linearly related to output by the XOR-operator. Our analysis reveals that the TM, with just two conjunctive clauses, can converge almost surely to reproducing XOR, learning from training data over an infinite time horizon. Furthermore, the analysis shows how the hyper-parameter T guides clause construction so that the clauses capture the distinct sub-patterns in the data. Our analysis of convergence for XOR thus lays the foundation for analyzing other more complex logical expressions. These analyses altogether, from a mathematical perspective, provide new insights on why TMs have obtained the state-of-the-art performance on several pattern recognition problems.

• Vishwanath, Ajay; Bøhn, Einar Duenger; Granmo, Ole-Christoffer; Maree, Charl & Omlin, Christian Walter Peter (2022). Towards artificial virtuous agents: games, dilemmas and machine learning. AI and Ethics. ISSN 2730-5953. doi: 10.1007/s43681-022-00251-8. Fulltekst i vitenarkiv
• Abouzeid, Ahmed Abdulrahem Othman & Granmo, Ole-Christoffer (2022). MMSS: A storytelling simulation software to mitigate misinformation on social media[Formula presented]. Software Impacts. 13. doi: 10.1016/j.simpa.2022.100341. Fulltekst i vitenarkiv Vis sammendrag

  This paper proposes a modular python implementation of a storytelling simulation. The software evaluates misinformation mitigation strategies over social media and visualizes the investigated scenarios’ potential outcomes. Our software integrates information diffusion and control models components. The control model mitigates users’ exposure to misinformation with social fairness awareness, while the diffusion model predicts the outcome from the control model. During the interaction of both models, a graph coloring algorithm traces the interaction within specific time intervals. Then, it generates meta-data to construct visuals of predicted near-future states of the social network to help support decision-making and evaluate proposed mitigation strategies.

• Rahman, Tousif; Shafik, Rishad; Granmo, Ole-Christoffer & Yakovlev, Alex (2022). Resilient Biomedical Systems Design Under Noise Using Logic-Based Machine Learning. Frontiers in Control Engineering. ISSN 2673-6268. doi: 10.3389/fcteg.2021.778118. Fulltekst i vitenarkiv
• Andersen, Per-Arne; Goodwin, Morten & Granmo, Ole-Christoffer (2022). CaiRL: A High-Performance Reinforcement Learning Environment Toolkit, 2022 IEEE Conference on Games (CoG). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665459891. s. 361–368. doi: 10.1109/CoG51982.2022.9893661. Fulltekst i vitenarkiv Vis sammendrag

  This paper addresses the dire need for a platform that efficiently provides a framework for running reinforcement learning (RL) experiments. We propose the CaiRL Environment Toolkit as an efficient, compatible, and more sustainable alternative for training learning agents and propose methods to develop more efficient environment simulations. There is an increasing focus on developing sustainable artificial intelligence. However, little effort has been made to improve the efficiency of running environment simulations. The most popular development toolkit for reinforcement learning, OpenAI Gym, is built using Python, a powerful but slow programming language. We propose a toolkit written in C++ with the same flexibility level but works orders of magnitude faster to make up for Python's inefficiency. This would drastically cut climate emissions. CaiRL also presents the first reinforcement learning toolkit with a built-in JVM and Flash support for running legacy flash games for reinforcement learning research. We demonstrate the effectiveness of CaiRL in the classic control benchmark, comparing the execution speed to OpenAI Gym. Furthermore, we illustrate that CaiRL can act as a drop-in replacement for OpenAI Gym to leverage significantly faster training speeds because of the reduced environment computation time.

• Giri, Charul; Granmo, Ole-Christoffer; Hoof, Herke Van & Blakely, Christian Dallas (2022). Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine, 2022 International Joint Conference on Neural Networks (IJCNN). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728186719. doi: 10.1109/IJCNN55064.2022.9892796. Fulltekst i vitenarkiv Vis sammendrag

  Hex is a turn-based two-player connection game with a high branching factor, making the game arbitrarily complex with increasing board sizes. As such, top-performing algorithms for playing Hex rely on accurate evaluation of board positions using neural networks. However, the limited interpretability of neural networks is problematic when the user wants to understand the reasoning behind the predictions made. In this paper, we propose to use propositional logic expressions to describe winning and losing board game positions, facilitating precise visual interpretation. We employ a Tsetlin Machine (TM) to learn these expressions from previously played games, describing where pieces must be located or not located for a board position to be strong. Extensive experiments on 6×6 boards compare our TM-based solution with popular machine learning algorithms like XGBoost, InterpretML, decision trees, and neural networks, considering various board configurations with 2 to 22 moves played. On average, the TM testing accuracy is 92.1%, outperforming all the other evaluated algorithms. We further demonstrate the global interpretation of the logical expressions, and map them down to particular board game configurations to investigate local interpretability. We believe the resulting interpretability establishes building blocks for accurate assistive AI and human-AI collaboration, also for more complex prediction tasks.

• Yadav, Rohan Kumar; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2022). Robust Interpretable Text Classification against Spurious Correlations Using AND-rules with Negation. I Raed, Luc de (Red.), Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. AAAI Press. ISSN 9781956792003. s. 4439–4446. doi: 10.24963/ijcai.2022/616. Fulltekst i vitenarkiv Vis sammendrag

  The state-of-the-art natural language processing models have raised the bar for excellent performance on a variety of tasks in recent years. However, concerns are rising over their primitive sensitivity to distribution biases that reside in the training and testing data. This issue hugely impacts the performance of the models when exposed to out-of-distribution and counterfactual data. The root cause seems to be that many machine learning models are prone to learn the shortcuts, modelling simple correlations rather than more fundamental and general relationships. As a result, such text classifiers tend to perform poorly when a human makes minor modifications to the data, which raises questions regarding their robustness. In this paper, we employ a rule-based architecture called Tsetlin Machine (TM) that learns both simple and complex correlations by ANDing features and their negations. As such, it generates explainable AND-rules using negated and non-negated reasoning. Here, we explore how non-negated reasoning can be more prone to distribution biases than negated reasoning. We further leverage this finding by adapting the TM architecture to mainly perform negated reasoning using the specificity parameter s. As a result, the AND-rules becomes robust to spurious correlations and can also correctly predict counterfactual data. Our empirical investigation of the model’s robustness uses the specifcity s to control the degree of negated reasoning. Experiments on publicly available Counterfactually-Augmented Data demonstrate that the negated clauses are robust to spurious correlations and outperform Naive Bayes, SVM, and Bi-LSTM by up to 20%, and ELMo by almost 6% on counterfactual test data.

• Yadav, Rohan Kumar; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Interpretability in Word Sense Disambiguation using Tsetlin Machine, Proceedings of the 13th International Conference on Agents and Artificial Intelligence (ICAART 2021). SciTePress. ISSN 9789897584848. s. 402–409. doi: 10.5220/0010382104020409. Fulltekst i vitenarkiv
• Abeyrathna, Kuruge Darshana; Rasca, Sinziana Ioana; Markvica, Karin & Granmo, Ole-Christoffer (2021). Public Transport Passenger Count Forecasting in Pandemic Scenarios Using Regression Tsetlin Machine. Case Study of Agder, Norway. Smart Innovation, Systems and Technologies. ISSN 2190-3018. 231, s. 27–37. doi: 10.1007/978-981-16-2324-0_4. Fulltekst i vitenarkiv
• Abeyrathna, Kuruge Darshana; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretability. IEEE Access. 9, s. 8233–8248. doi: 10.1109/ACCESS.2021.3049569. Fulltekst i vitenarkiv
• Andersen, Per-Arne; Goodwin, Morten & Granmo, Ole-Christoffer (2021). ORACLE: End-to-End Model Based Reinforcement Learning. I Bramer, Max & Ellis, Richard (Red.), Artificial Intelligence XXXVIII, 41st SGAI International Conference on Artificial Intelligence. Springer. ISSN 9783030910990. doi: 10.1007/978-3-030-91100-3_4. Fulltekst i vitenarkiv
• Yadav, Rohan Kumar; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Enhancing Interpretable Clauses Semantically using Pretrained Word Representation, Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics (ACL). ISSN 9781955917063. s. 265–274. doi: 10.18653/v1/2021.blackboxnlp-1.19. Fulltekst i vitenarkiv
• Abeyrathna, Kuruge Darshana; Granmo, Ole-Christoffer; Shafik, Rishad; Lei, Jiao; Wheeldon, Adrian & Yakovlev, Alex [Vis alle 8 forfattere av denne artikkelen] (2021). A multi-step finite-state automaton for arbitrarily deterministic Tsetlin Machine learning. Expert Systems. ISSN 0266-4720. 40(4). doi: 10.1111/exsy.12836. Fulltekst i vitenarkiv
• Abeyrathna, Kuruge Darshana; Bhattarai, Bimal; Goodwin, Morten; Gorji, Saeed Rahimi; Granmo, Ole-Christoffer & Lei, Jiao [Vis alle 8 forfattere av denne artikkelen] (2021). Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling. Proceedings of Machine Learning Research (PMLR). Fulltekst i vitenarkiv Vis sammendrag

  Using logical clauses to represent patterns, Tsetlin Machine (TM) have recently obtained competitive performance in terms of accuracy, memory footprint, energy, and learning speed on several benchmarks. Each TM clause votes for or against a particular class, with classification resolved using a majority vote. While the evaluation of clauses is fast, being based on binary operators, the voting makes it necessary to synchronize the clause evaluation, impeding parallelization. In this paper, we propose a novel scheme for desynchronizing the evaluation of clauses, eliminating the voting bottleneck. In brief, every clause runs in its own thread for massive native parallelism. For each training example, we keep track of the class votes obtained from the clauses in local voting tallies. The local voting tallies allow us to detach the processing of each clause from the rest of the clauses, supporting decentralized learning. This means that the TM most of the time will operate on outdated voting tallies. We evaluated the proposed parallelization across diverse learning tasks and it turns out that our decentralized TM learning algorithm copes well with working on outdated data, resulting in no significant loss in learning accuracy. Furthermore, we show that the approach provides up to 50 times faster learning. Finally, learning time is almost constant for reasonable clause amounts (employing from 20 to 7,000 clauses on a Tesla V100 GPU). For sufficiently large clause numbers, computation time increases approximately proportionally. Our parallel and asynchronous architecture thus allows processing of more massive datasets and operating with more clauses for higher accuracy.

• Yadav, Rohan Kumar; Lei, Jiao; Goodwin, Morten & Granmo, Ole-Christoffer (2021). Positionless aspect based sentiment analysis using attention mechanism. Knowledge-Based Systems. ISSN 0950-7051. 226. doi: 10.1016/j.knosys.2021.107136. Fulltekst i vitenarkiv
• Abouzeid, Ahmed Abdulrahem Othman; Granmo, Ole-Christoffer; Webersik, Christian & Goodwin, Morten (2021). Learning Automata-based Misinformation Mitigation via Hawkes Processes. Information Systems Frontiers. ISSN 1387-3326. 23, s. 1169–1188. doi: 10.1007/s10796-020-10102-8. Fulltekst i vitenarkiv Vis sammendrag

  Mitigating misinformation on social media is an unresolved challenge, particularly because of the complexity of information dissemination. To this end, Multivariate Hawkes Processes (MHP) have become a fundamental tool because they model social network dynamics, which facilitates execution and evaluation of mitigation policies. In this paper, we propose a novel light-weight intervention-based misinformation mitigation framework using decentralized Learning Automata (LA) to control the MHP. Each automaton is associated with a single user and learns to what degree that user should be involved in the mitigation strategy by interacting with a corresponding MHP, and performing a joint random walk over the state space. We use three Twitter datasets to evaluate our approach, one of them being a new COVID-19 dataset provided in this paper. Our approach shows fast convergence and increased valid information exposure. These results persisted independently of network structure, including networks with central nodes, where the latter could be the root of misinformation. Further, the LA obtained these results in a decentralized manner, facilitating distributed deployment in real-life scenarios.

• Abouzeid, Ahmed Abdulrahem Othman; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Modelling Emotion Dynamics in Chatbots with Neural Hawkes Processes. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. doi: 10.1007/978-3-030-91100-3_12. Fulltekst i vitenarkiv
• Gorji, Saeed Rahimi; Granmo, Ole-Christoffer & Wiering, Marco (2021). Explainable Reinforcement Learning with the Tsetlin Machine. I Fujita, Hamido (Red.), Advances and Trends in Artificial Intelligence. Artificial Intelligence Practices. Springer Nature. ISSN 9783030794569. Fulltekst i vitenarkiv
• Saha, Rupsa; Granmo, Ole-Christoffer; Zadorozhny, Vladimir & Goodwin, Morten (2021). A relational Tsetlin Machine with applications to natural language understanding. Journal of Intelligent Information Systems. ISSN 0925-9902. doi: 10.1007/s10844-021-00682-5. Fulltekst i vitenarkiv
• Bhattarai, Bimal; Granmo, Ole-Christoffer & Jiao, Lei (2021). Measuring the Novelty of Natural Language Text using the Conjunctive Clauses of a Tsetlin Machine Text Classifier, Proceedings of the 13th International Conference on Agents and Artificial Intelligence (ICAART 2021). SciTePress. ISSN 9789897584848. s. 410–417. doi: 10.5220/0010382204100417. Fulltekst i vitenarkiv Vis sammendrag

  Most supervised text classification approaches assume a closed world, counting on all classes being present in the data at training time. This assumption can lead to unpredictable behaviour during operation, whenever novel, previously unseen, classes appear. Although deep learning-based methods have recently been used for novelty detection, they are challenging to interpret due to their black-box nature. This paper addresses interpretable open-world text classification, where the trained classifier must deal with novel classes during operation. To this end, we extend the recently introduced Tsetlin machine (TM) with a novelty scoring mechanism. The mechanism uses the conjunctive clauses of the TM to measure to what degree a text matches the classes covered by the training data. We demonstrate that the clauses provide a succinct interpretable description of known topics, and that our scoring mechanism makes it possible to discern novel topics from the known ones. Empirically, our TM-b ased approach outperforms seven other novelty detection schemes on three out of five datasets, and performs second and third best on the remaining, with the added benefit of an interpretable propositional logic-based representation.

• Yadav, Rohan Kumar; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Human-Level Interpretable Learning for Aspect-Based Sentiment Analysis. Proceedings of the AAAI Conference on Artificial Intelligence. ISSN 2159-5399. s. 14203–14212. Fulltekst i vitenarkiv Vis sammendrag

  This paper proposes human-interpretable learning of aspect-based sentiment analysis (ABSA), employing the recently introduced Tsetlin Machines (TMs). We attain interpretability by converting the intricate position-dependent textual semantics into binary form, mapping all the features into bag-of-words (BOWs). The binary form BOWs are encoded so that the information on the aspect and context words are nearly lossless for sentiment classification. We further adapt the BOWs as input to the TM, enabling learning of aspect-based sentiment patterns in propositional logic. To evaluate interpretability and accuracy, we conducted experiments on two widely used ABSA datasets of SemEval 2014: Restaurant 14 and Laptop 14. The experiments show how each relevant feature takes part in conjunctive clauses that contain the context information for the corresponding aspect word, demonstrating human-level interpretability. At the same time, the obtained accuracy is competitive with existing neural network models, reaching 78.02% on Restaurant 14 and 73.51% on Laptop 14.

• Sharma, Jivitesh; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Emergency Analysis: Multitask Learning with Deep Convolutional Neural Networks for Fire Emergency Scene Parsing. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. Fulltekst i vitenarkiv
• Bhattarai, Bimal; Granmo, Ole-Christoffer & Jiao, Lei (2021). A Tsetlin Machine Framework for Universal Outlier and Novelty Detection, Proceedings of the 13th International Conference on Agents and Artificial Intelligence (ICAART 2021). SciTePress. ISSN 9789897584848. doi: 10.1007/978-3-031-10161-8_14. Fulltekst i vitenarkiv
• Abeyrathna, Kuruge Darshana; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Convolutional Regression Tsetlin Machine: An Interpretable Approach to Convolutional Regression, 2021 6th International Conference on Machine Learning Technologies. Association for Computing Machinery (ACM). ISSN 9781450389402. s. 65–70. doi: 10.1145/3468891.3468901. Fulltekst i vitenarkiv Vis sammendrag

  The Convolutional Tsetlin Machine (CTM), a variant of Tsetlin Machine (TM), represents patterns as straightforward AND-rules, to address the high computational complexity and the lack of interpretability of Convolutional Neural Networks (CNNs). CTM has shown competitive performance on MNIST, Fashion-MNIST, and Kuzushiji-MNIST pattern classification benchmarks, both in terms of accuracy and memory footprint. In this paper, we propose the Convolutional Regression Tsetlin Machine (C-RTM) that extends the CTM to support continuous output problems in image analysis. C-RTM identifies patterns in images using the convolution operation as in the CTM and then maps the identified patterns into a real-valued output as in the Regression Tsetlin Machine (RTM). The C-RTM thus unifies the two approaches. We evaluated the performance of C-RTM using 72 different artificial datasets, with and without noise in the training data. Our empirical results show the competitive performance of C-RTM compared to two standard CNNs. Additionally, the interpretability of the identified sub-patterns by C-RTM clauses is analyzed and discussed.

• Sharma, Jivitesh; Andersen, Per-Arne; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Deep Q-Learning with Q-Matrix Transfer Learning for Novel Fire Evacuation Environment. IEEE Transactions on Systems, Man & Cybernetics. Systems. ISSN 2168-2216. 51(12), s. 7363–7381. doi: 10.1109/TSMC.2020.2967936. Fulltekst i vitenarkiv
• Saha, Rupsa; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Using Tsetlin Machine to discover interpretable rules in natural language processing applications. Expert Systems. ISSN 0266-4720. doi: 10.1111/exsy.12873. Fulltekst i vitenarkiv Vis sammendrag

  Tsetlin Machines (TM) use finite state machines for learning and propositional logic to represent patterns. The resulting pattern recognition approach captures information in the form of conjunctive clauses, thus facilitating human interpretation. In this work, we propose a TM-based approach to three common natural language processing (NLP) tasks, namely, sentiment analysis, semantic relation categorization and identifying entities in multi-turn dialogues. By performing frequent itemset mining on the TM-produced patterns, we show that we can obtain a global and a local interpretation of the learning, one that mimics existing rule-sets or lexicons. Further, we also establish that our TM based approach does not compromise on accuracy in the quest for interpretability, via comparison with some widely used machine learning techniques. Finally, we introduce the idea of a relational TM, which uses a logic-based framework to further extend the interpretability.

• Abeyrathna, Kuruge Darshana; Granmo, Ole-Christoffer & Goodwin, Morten (2021). Adaptive sparse representation of continuous input for tsetlin machines based on stochastic searching on the line. Electronics (Basel). 10(17). doi: 10.3390/electronics10172107. Fulltekst i vitenarkiv
• Zhang, Xuan; Lei, Jiao; Granmo, Ole-Christoffer & Goodwin, Morten (2021). On the convergence of Tsetlin machines for the IDENTITY- and NOT operators. IEEE Transactions on Pattern Analysis and Machine Intelligence. ISSN 0162-8828. 44(10), s. 6345–6359. doi: 10.1109/TPAMI.2021.3085591. Fulltekst i vitenarkiv
• Gorji, Saeed Rahimi; Granmo, Ole-Christoffer; Glimsdal, Sondre; Edwards, Jonathan & Goodwin, Morten (2020). Increasing the Inference and Learning Speed of Tsetlin Machines with Clause Indexing, Trends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices.. Springer Nature. ISSN 9783030557898. s. 695–708. doi: 10.1007/978-3-030-55789-8_60. Fulltekst i vitenarkiv

Se alle arbeider i NVA

• Shafik, Rishad; Granmo, Ole-Christoffer; Lei, Jiao & Zadorozhny, Vladimir (2022). 2022 International Symposium on the Tsetlin Machine (ISTM 2022). IEEE (Institute of Electrical and Electronics Engineers). ISBN 9781665471169. Fulltekst i vitenarkiv
• Sanfilippo, Filippo; Granmo, Ole-Christoffer; Yayilgan, Sule Yildirim & Bajwa, Imran Sarwar (2022). Intelligent Technologies and Applications: 4th International Conference, INTAP 2021, Grimstad, Norway, October 11–13, 2021, Revised Selected Papers. Springer. ISBN 9783031105241. 434 s. Fulltekst i vitenarkiv

Se alle arbeider i NVA

• Grønningsæter, Ylva; Smørvik, Halvor S. & Granmo, Ole-Christoffer (2024). An Optimized Toolbox for Advanced Image Processing with Tsetlin Machine Composites. Fulltekst i vitenarkiv
• Jenssen, Robert; Granmo, Ole-Christoffer & Borgan, Eldrid (2024). Kan norsk oppfinnelse revolusjonere kunstig intelligens? [Internet]. Forskning.no. Fulltekst i vitenarkiv
• Granmo, Ole-Christoffer (2024). Tutorial: An Introduction to the Tsetlin Machine. Fulltekst i vitenarkiv
• Sahu, Prajwal Kumar; Boppu, Srinivas; Shafik, Rishad Ahmed; Tunheim, Svein Anders; Granmo, Ole-Christoffer & Cenkeramaddi, Linga Reddy (2023). Enhancing Inference Performance through Include only Literal Incorporation in Tsetlin Machine. Fulltekst i vitenarkiv
• Granmo, Ole-Christoffer (2023). Om 5 år vil det være noe helt annet å være utvikler, mener norsk AI-ekspert. [Internet]. kode24. Fulltekst i vitenarkiv
• Liland, Kristian Hovde; Tomic, Oliver; Indahl, Ulf Geir; Futsæther, Cecilia Marie; Jiao, Lei & Granmo, Ole-Christoffer [Vis alle 7 forfattere av denne artikkelen] (2023). Tsetlin Machine in DNA sequence classification. Fulltekst i vitenarkiv Vis sammendrag

  The Tsetlin machine (TM) is a logic-based machine learning model with the crucial advantages of transparency and hardware-friendliness. In TM, groups of Tsetlin Automata (TAs) produce Boolean expressions in the form of conjunctive clauses in AND-rules. In this work, we show that the DNA nucleotide sequence, coded using the four-letter alphabet A, C, G, T, is a perfect match to the Boolean logic-based TM. A coalesced integer-weighted TM is applied to the problem of prokaryote gene prediction demonstrating beyond state-of-the-art performance on reference genomes. This paves the way for highly efficient bioinformatic analysis in a large range of applications.

• Przybysz, Emilia; Bhattarai, Bimal; Persia, Cosimo Damiano; Ozaki, Ana; Granmo, Ole-Christoffer & Sharma, Jivitesh (2023). Verifying Properties of Tsetlin Machines. Fulltekst i vitenarkiv
• Tunheim, Svein Anders; Lei, Jiao & Granmo, Ole-Christoffer (2023). Model Export for the Convolutional Coalesced Tsetlin Machine. Fulltekst i vitenarkiv
• Bhattarai, Bimal & Granmo, Ole-Christoffer (2022). Tsetlin Machine Applications. Fulltekst i vitenarkiv
• Granmo, Ole-Christoffer & Bhattarai, Bimal (2022). Tsetlin Machine – efficient AI technology for language processing. Fulltekst i vitenarkiv
• Granmo, Ole-Christoffer (2022). Nå skal den norske Tsetlin-maskinen videreutvikles. [Internet]. digi.no. Fulltekst i vitenarkiv
• Granmo, Ole-Christoffer (2022). Sannheten om Kunstig Intelligens. Fulltekst i vitenarkiv
• Granmo, Ole-Christoffer (2022). The Tsetlin Machine – From Arithmetic to Logic-based AI. Fulltekst i vitenarkiv
• Holen, Martin; Ruud, Else-Line Malene; Warakagoda, Narada Dilp; Granmo, Ole-Christoffer; Engelstad, Paal E. & Knausgård, Kristian Muri (2022). Towards Using Reinforcement Learning for Autonomous Docking of Unmanned Surface Vehicles. doi: 10.1007/978-3-031-08223-8_38. Fulltekst i vitenarkiv Vis sammendrag

  Providing full autonomy to Unmanned Surface Vehicles (USV) is a challenging goal to achieve. Autonomous docking is a subtask that is particularly difficult. The vessel has to distinguish between obstacles and the dock, and the obstacles can be either static or moving. This paper developed a simulator using Reinforcement Learning (RL) to approach the problem. We studied several scenarios for the task of docking a USV in a simulator environment. The scenarios were defined with different sensor inputs and start-stop procedures but a simple shared reward function. The results show that the system solved the task when the IMU (Inertial Measurement Unit) and GNSS (Global Navigation Satellite System) sensors were used to estimate the state, despite the simplicity of the reward function.

• Lei, Jiao; Granmo, Ole-Christoffer; Blakely, Christian Dallas & Zadorozhny, Vladimir (2021). Denne chipen skjuler en norsk oppfinnelse som kan redde liv. [Internet]. NRK. Fulltekst i vitenarkiv
• Sanfilippo, Filippo; Bajwa, Imran Sarwar; Granmo, Ole-Christoffer & Yayilgan, Sule Yildirim (2021). 4th International Conference on Intelligent Technologies and Applications (INTAP'21). Fulltekst i vitenarkiv
• Abouzeid, Ahmed Abdulrahem Othman & Granmo, Ole-Christoffer (2023). Optimization of Multivariate Hawkes Processes via Decentralized Learning Automata: Towards Learning How to Boost Factual Information on Social Networks. Universitetet i Agder. ISSN 9788284271569. Fulltekst i vitenarkiv Vis sammendrag

  The increasing amount of misleading information on Social Media (SM) platforms is problematic. The reason is that these platforms have become one of the primary sources of information due to their ease-of-use and cheap cost of information acquisition. One example is that misleading information can disturb the social order and recovery from emergencies, recently actualized by the infodemic of COVID-19 and the Russian-Ukrainian information war. As the amount of misleading information on SM increases, we risk that consumers start mistrusting even reliable information sources. To this end, a wide range of Artificial Intelligence (AI)-based solutions were proposed to combat such an issue. One common approach is the intervention-based misinformation mitigation on SM, where the task is to mitigate the exposure to misinformation by alternatively boosting the exposure to factual information. Traditionally, the exposure to a particular information type for each user is defined as the count of propagated content of that information type by the adjacents of that user, e.g., followees on Twitter. To boost exposure to online factual content, SM users are incentivized to propagate these facts first, and their network adjacents such as their followers on Twitter can then reach and interact with these facts. Hence, in this context, intervening with users means incentivizing them to change their information dissemination behavior by propagating more factual information. Because each user has a different number of adjacent users and each user has a different level of exposure to misinformation, the individual incentives should be determined differently according to the following. On one hand, (A) how much misinformation exposure a user has? On the other hand, (B) how much exposure to misinformation do adjacent users have? In all cases, (C) How likely are a user or the adjacent users will accept or be influenced by the determined incentivization? Traditionally, the learning of individual incentives is facilitated through the Reinforcement Learning (RL) framework. In the latter, the dynamics of SM users’ online engagements are modeled through a simulated social network environment from which the RL agents can learn about users’ behavior. However, there have been relatively few intakes on how to learn and evaluate the optimal individual incentivization required to achieve optimal mitigation outcomes. For instance, existing criterion functions and representations mainly focused on quantities of misinformation and factual information which each user is exposed to, without considering the root causes that drive these exposures. Hence, the answer to question (C) was not investigated adequately. We believe the latter is a noticeable drawback in the proposed solutions because the simulated network and the incentivization procedure should be conducted over the best possible representation and criterion function that reflect real-world dynamics on SM. In this research, we propose a novel approach utilizing RL, specifically Learning Automaton (LA). Our method combines the principles of RL with the adaptive decision-making capabilities of LA to address the challenges of user needs-based incentivization learning. Further, we propose a novel simulation-based optimization framework with novel users’ activity representation to model the task of interventionbased misinformation mitigation. Driven by the novel activity representation, we propose a novel criterion function that considers the key factors that influence information propagation on SM instead of only calculating quantities of misinformation and factual information exposures. These key factors were proposed in recent Social Science literature and illustrated what dictates misinformation spread on today’s SM platforms. In that manner, we propose temporal activities of societal bias, content engagement, and the propagation patterns of both misinformation and factual information. Thus, we do not assume incentives to be assigned based on the quantities of exposure to misinformation only but rather evaluated and assigned based on the probability of agreeing with a content or an opinion that has a particular bias, in addition to the probability of engaging with it in the first place. Further, the study proposes preliminary algorithms to help verify and self-learning of SM activity categories such as political bias and information type. Finally, our empirical results show three main significant properties. First, they demonstrate how our novel mitigation algorithms perform better in most of the scenarios when compared to traditional RL algorithms. Second, the results indicate how our proposed criterion functions are robust to different network statistics in terms of different percentages of misinformation exposure among users. Third, our novel activity representation is more transparent and extended the analytical capacity to a misinformation mitigation solution. The latter is recognized in the provided capabilities of tracing the change in probabilities of societal bias and content engagement as a consequence of the intervention. In all brevity, this research investigates questions and problem variables beyond the existing misinformation benchmark datasets and their underlying representations. The study gathered additional comprehensive and crucial data to create a well-developed learning setting and standard for the proposed LA agent. Our research aims to connect the realms of AI and Social Science by examining pertinent theoretical studies concerning the issue of misinformation spreading on SM and the interconnected dynamics that oversee this process

• Andersen, Per-Arne; Goodwin, Morten & Granmo, Ole-Christoffer (2022). Advancements in Safe Deep Reinforcement Learning for Real-Time Strategy Games and Industry Applications. Universitetet i Agder. ISSN 9788284270708. Fulltekst i vitenarkiv Vis sammendrag

  Deep reinforcement learning has attracted considerable attention from industry and academia, among others, because of its success in solving intricate video games and industrial applications. Recent advancements in hardware and computing exponentially increase computational power availability, facilitating deep neural networks training. These networks can learn the RL behavior policy from high-dimensional data and perform significantly better than exact tabular solutions, albeit requiring considerably more computer resources. Games are among the most used applications to assess reinforcement learning (RL) algorithms’ behavioral properties and planning efficiency. They can provide the data structure and volume required to train deep learning models. Specially crafted games can express real-world industry applications to reduce setup costs while drastically increasing reproducibility. RL can improve efficiency in industrial applications where expert systems dominate the scene, reduce manual and potentially dangerous labor. The problem with applied industrial reinforcement learning is that traditional methods learn by trial and error. Because of this, RL agents risk encountering catastrophic events during learning, which can cause damage to humans or equipment. Therefore, using games to train and study safe RL agents is appealing. Real-Time Strategy (RTS) games are especially captivating because of their high dimensional state and action spaces. Furthermore, RTS games share many attributes with industrial and real-world applications, such as simultaneous actions, imperfect information, and system stochasticity. Recent advancements show that model-free RL algorithms can learn superhuman performance in games such as StarCraft II, again using substantial computational power. Therefore, the downside is that these algorithms are expensive and hard to train, making it challenging to use the same methods for industrial applications. There are also substantial state-space complexity gaps in open-source environments. This restricts algorithm evaluation to only a subset of tasks required for operating sufficiently in industry applications.

Se alle arbeider i NVA