# Verifying Properties of Tsetlin Machines

arXiv: https://arxiv.org/abs/2303.14464 · HTML: https://mlsanity.com/paper/2303.14464/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## Builds on (most cited first, 10 of 10)

- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Verifying Properties of Binarized Deep Neural Networks](https://mlsanity.com/paper/1709.06662/) (2017)
- [The Tsetlin Machine -- A Game Theoretic Bandit Driven Approach to Optimal Pattern Recognition with Propositional Logic](https://mlsanity.com/paper/1804.01508/) (2018)
- [The Convolutional Tsetlin Machine](https://mlsanity.com/paper/1905.09688/) (2019)
- [Efficient Exact Verification of Binarized Neural Networks](https://mlsanity.com/paper/2005.03597/) (2020)
- [Using the Tsetlin Machine to Learn Human-Interpretable Rules for High-Accuracy Text Categorization with Medical Applications](https://mlsanity.com/paper/1809.04547/) (2018)
- [On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operators](https://mlsanity.com/paper/2007.14268/) (2020)
- [Extending the Tsetlin Machine With Integer-Weighted Clauses for Increased Interpretability](https://mlsanity.com/paper/2005.05131/) (2020)
- [Low-Power Audio Keyword Spotting using Tsetlin Machines](https://mlsanity.com/paper/2101.11336/) (2021)
- [Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin Machine](https://mlsanity.com/paper/2105.14506/) (2021)

## Abstract (arXiv)

Tsetlin Machines (TsMs) are a promising and interpretable machine learning method which can be applied for various classification tasks. We present an exact encoding of TsMs into propositional logic and formally verify properties of TsMs using a SAT solver. In particular, we introduce in this work a notion of similarity of machine learning models and apply our notion to check for similarity of TsMs. We also consider notions of robustness and equivalence from the literature and adapt them for TsMs. Then, we show the correctness of our encoding and provide results for the properties: adversarial robustness, equivalence, and similarity of TsMs. In our experiments, we employ the MNIST and IMDB datasets for (respectively) image and sentiment classification. We discuss the results for verifying robustness obtained with TsMs with those in the literature obtained with Binarized Neural Networks on MNIST.