An Introduction to the Tsetlin Machine

Discover the Tsetlin Machine, an AI method that learns logical, human-understandable rules while matching neural networks in performance. Led by Prof. Ole-Christoffer Granmo, this seminar covers its fundamentals, applications, and recent advancements.

Open to students and researchers. Free event sponsored by Norwegian AI Cloud (NAIC). Register now!

Time and place: – , Zoom link for the event?will be sent to the participants in a separete mail
Bildet kan inneholde: funksjon?r, utgivelse.

Free event sponsored by Norwegian AI Cloud (NAIC). Register now!

Register now!

Register for the Workshop

Course description 

The Tsetlin machine is a new universal artificial intelligence (AI) method that learns simple logical rules to understand complex things, similar to how an infant uses logic to learn about the world. Being logical, the rules become understandable to humans. Yet, unlike all other intrinsically explainable techniques, Tsetlin machines are drop-in replacements for neural networks by supporting classification, convolution, regression, reinforcement learning, auto-encoding, language models, and natural language processing. They are further ideally suited for cutting-edge hardware solutions of low cost, enabling nanoscale intelligence, ultralow energy consumption, energy harvesting, unrivalled inference speed, and competitive accuracy. In this seminar, the basics and recent advances of Tsetlin machines, including inference and learning, advanced architectures, and applications, will be covered. 

The workshop is sponsored by the NAIC (Norwegian AI Cloud) project with the RCN Grant Number: 322336. 

Target audience 

Graduate and undergraduate students, as well as researchers. 

Learning outcomes 

The student will get in-depth knowledge of selected advanced topics in Tsetlin machines, obtaining both theoretical and practical skills. The student will further be able to analyse, implement, and evaluate the main Tsetlin machine architectures, including regression, convolution, auto-encoding, and composites. Finally, the student will know how to apply the architectures within image analysis, natural language processing, and board games. 

Prerequisites and required materials 

Basic understanding of machine learning, algorithms, and statistics (Bachelor level 

Lecturer 

Prof. Ole-Christoffer Granmo?is the Founding Director of the?Centre for Artificial Intelligence Research (CAIR)?at the University of Agder, Norway. He obtained his master’s degree in 1999 and his PhD degree in 2004, both from the University of Oslo, Norway. In 2018, he created the?Tsetlin machine, for which he was awarded the AI research paper of the decade by the?Norwegian Artificial Intelligence Consortium (NORA)?in 2022. Dr. Granmo has authored 180+ refereed papers with nine paper awards in machine learning, encompassing learning automata, bandit algorithms, Tsetlin machines, Bayesian reasoning, reinforcement learning, and computational linguistics. He has further coordinated 7+ research projects and graduated 55+ master- and nine PhD students. Dr. Granmo is also a co-founder of NORA. Apart from his academic endeavors, he co-founded?Anzyz Technologies AS?and is the Chair of the Technical Steering Committee at?Literal Labs. 

Organiser  

Norwegian AI Cloud & dScience – Centre for Computational and Data Science – at the University of Oslo (UiO)

 

Textbooks 

  • An Introduction to Tsetlin Machines. Ole-Christoffer Granmo (https://tsetlinmachine.org) 

  • Learning Automata:An Introduction.?Kumpati S. Narendra and Mandayam A. L. Thathachar. Prentice-Hall, 1989 

Research Literature 

  • B. Tung and L. Kleinrock: Using finite state automata to produce self-optimization and self-control. IEEE Transactions on Parallel and Distributed Systems: vol. 7, no. 4, pp. 439-448, April 1996, doi: 10.1109/71.494637 

  • Chapter 1 of An Introduction to Tsetlin Machines (https://tsetlinmachine.org) 

  • Ole-Christoffer Granmo: The Tsetlin Machine - A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic. CoRR abs/1804.01508 (2018)?https://arxiv.org/abs/1804.01508 

  • Rohan Kumar Yadav, Lei Jiao, Ole-Christoffer Granmo, Morten Goodwin: Robust Interpretable Text Classification against Spurious Correlations Using AND-rules with Negation. IJCAI 2022: 4439-4446 (2022)?https://doi.org/10.24963/ijcai.2022/616 

  • Jinbao Zhang, Xuan Zhang, Lei Jiao, Ole-Christoffer Granmo, Yongjun Qian, Fan Pan: Interpretable Tsetlin Machine-based Premature Ventricular Contraction Identification. CoRR abs/2301.10181 (2023)?https://arxiv.org/abs/2301.10181 

  • Charul Giri, Ole-Christoffer Granmo, Herke Van Hoof, and Christian D. Blakely: Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine. International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 2022, pp. 1-9 (2022)?https://doi.org/10.1109/IJCNN55064.2022.9892796 

  • Abu Bakar, Tousif Rahman, Rishad Shafik, Fahim Kawsar, and Alessandro Montanari: Adaptive Intelligence for Batteryless Sensors Using Software-Accelerated Tsetlin Machines. In Proceedings of the 20th ACM Conference on Embedded Networked Sensor Systems (SenSys '22). Association for Computing Machinery, New York, NY, USA, 236–249 (2022)?https://doi.org/10.1145/3560905.356851 

  • Xuan Zhang, Lei Jiao, Ole-Christoffer Granmo, Morten Goodwin: On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operators. IEEE Trans. Pattern Anal. Mach. Intell. 44(10): 6345-6359 (2022)?https://ieeexplore.ieee.org/document/9445039 

  • Lei Jiao, Xuan Zhang, Ole-Christoffer Granmo, Kuruge Darshana Abeyrathna: On the Convergence of Tsetlin Machines for the XOR Operator. IEEE Trans. Pattern Anal. Mach. Intell. 45(5): 6072-6085 (2023) 

  • Darshana Abeyrathna K., Granmo Ole-Christoffer, Zhang Xuan, Jiao Lei, and Goodwin Morten: The regression Tsetlin machine: a novel approach to interpretable nonlinear regression. Phil. Trans. R. Soc. A. 378 (2019)?http://doi.org/10.1098/rsta.2019.0165 

  • Svein Anders Tunheim, Lei Jiao, Rishad A. Shafik, Alex Yakovlev, Ole-Christoffer Granmo: Convolutional Tsetlin Machine-based Training and Inference Accelerator for 2-D Pattern Classification. Microprocess. Microsystems 103: 104949 (2023)?https://doi.org/10.1016/j.micpro.2023.104949 

  • Bimal Bhattarai, Ole-Christoffer Granmo, Lei Jiao, Rohan Kumar Yadav, and Jivitesh Sharma: Tsetlin Machine Embedding: Representing Words Using Logical Expressions. Findings of the Association for Computational Linguistics: EACL 2024 EACL.?https://arxiv.org/abs/2301.00709 

 

 

Register now!

Register for the Workshop

Published Mar. 3, 2025 9:54 AM - Last modified Mar. 7, 2025 12:06 PM
E-mail this page