mlsanityData to 7 Oct 2026

Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines

arXiv 2406.02648 ↗First posted 4 Jun 2024cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

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 not 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 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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

29 of 53 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  6. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  7. 2020Contrastive Learning with Hard Negative Samplescited by 619
  8. 2019Learning the Difference that Makes a Difference with Counterfactually-Augmented Datacited by 428
  9. 2020Hard Negative Mixing for Contrastive Learningcited by 399
  10. 2017Sampling Matters in Deep Embedding Learningcited by 285
  11. 2020Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningcited by 275
  12. 2022The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrinkcited by 183
17 more
  1. 2018The Tsetlin Machine -- A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logiccited by 71
  2. 2020A comparison of Vector Symbolic Architecturescited by 63
  3. 2019The Convolutional Tsetlin Machinecited by 37
  4. 2018Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization with Medical Applicationscited by 24
  5. 2020On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operatorscited by 23
  6. 2021Coalesced Multi-Output Tsetlin Machines with Clause Sharingcited by 22
  7. 2020Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scalingcited by 20
  8. 2022Understanding Hyperdimensional Computing for Parallel Single-Pass Learningcited by 20
  9. 2020Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretabilitycited by 16
  10. 2021On the Convergence of Tsetlin Machines for the XOR Operatorcited by 16
  11. 2020ChewBaccaNN: A Flexible 223 TOPS/W BNN Acceleratorcited by 7
  12. 2021Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin Machinecited by 7
  13. 2023Learning from Hypervectors: A Survey on Hypervector Encodingcited by 7
  14. 2020Closed-Form Expressions for Global and Local Interpretation of Tsetlin Machines with Applications to Explaining High-Dimensional Datacited by 6
  15. 2019A Tsetlin Machine with Multigranular Clausescited by 5
  16. 2020A Novel Multi-Step Finite-State Automaton for Arbitrarily Deterministic Tsetlin Machine Learningcited by 5
  17. 2020Increasing the Inference and Learning Speed of Tsetlin Machines with Clause Indexingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025Scalable Multi-phase Word Embedding Using Conjunctive Propositional Clausescited by 2
  2. 2025The Tsetlin Machine Goes Deep: Logical Learning and Reasoning With Graphscited by 2
  3. 2024Hyperdimensional Vector Tsetlin Machines with Applications to Sequence Learning and Generationcited by 0
  4. 2025A Comparative Study of Feature Selection in Tsetlin Machinescited by 0
  5. 2026Macroeconomic Message Passing for Anticipating Foreign Exchange Regime Changes: A Deep Logical Learning Approach using Graph Tsetlin Machinescited by 0