# A Novel Multi-Step Finite-State Automaton for Arbitrarily Deterministic Tsetlin Machine Learning

arXiv: https://arxiv.org/abs/2007.02114 · HTML: https://mlsanity.com/paper/2007.02114/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Coalesced Multi-Output Tsetlin Machines with Clause Sharing](https://mlsanity.com/paper/2108.07594/) (2021)
- [Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size](https://mlsanity.com/paper/2301.08190/) (2023)
- [Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines](https://mlsanity.com/paper/2406.02648/) (2024)
- [Self-timed Reinforcement Learning using Tsetlin Machine](https://mlsanity.com/paper/2109.00846/) (2021)
- [The Probabilistic Tsetlin Machine: A Novel Approach to Uncertainty Quantification](https://mlsanity.com/paper/2410.17851/) (2024)

## Abstract (arXiv)

Due to the high energy consumption and scalability challenges of deep learning, there is a critical need to shift research focus towards dealing with energy consumption constraints. Tsetlin Machines (TMs) are a recent approach to machine learning that has demonstrated significantly reduced energy usage compared to neural networks alike, while performing competitively accuracy-wise on several benchmarks. However, TMs rely heavily on energy-costly random number generation to stochastically guide a team of Tsetlin Automata to a Nash Equilibrium of the TM game. In this paper, we propose a novel finite-state learning automaton that can replace the Tsetlin Automata in TM learning, for increased determinism. The new automaton uses multi-step deterministic state jumps to reinforce sub-patterns. Simultaneously, flipping a coin to skip every d'th state update ensures diversification by randomization. The d-parameter thus allows the degree of randomization to be finely controlled. E.g., d=1 makes every update random and d=∞ makes the automaton completely deterministic. Our empirical results show that, overall, only substantial degrees of determinism reduces accuracy. Energy-wise, random number generation constitutes switching energy consumption of the TM, saving up to 11 mW power for larger datasets with high d values. We can thus use the new d-parameter to trade off accuracy against energy consumption, to facilitate low-energy machine learning.