Logic-Based Machine Learning with Reproducible Decision Model Using the Tsetlin Machine

Tsetlin Machine (TM) is a recent automaton-based algorithm for reinforcement learning. It has demonstrated competitive accuracy on many popular benchmarks while providing a natural interpretability. Due to its logically underpinning it is amenable to hardware implementation with faster performance a...

Full description

Saved in:
Bibliographic Details
Main Authors: Tarasyuk, Olga, Gorbenko, Anatoliy, Rahman, Tousif, Shafik, Rishad, Yakovlev, Alex
Format: Conference Proceeding
Language:English
Subjects:
architecture
Artificial neural networks
Benchmark testing
hyperparameters
learning automaton
learning reproducibility
logic-based artificial intelligence
machine learning
Neurons
Productivity
Reinforcement learning
Reproducibility of results
Stochastic processes
tsetlin machine
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Tsetlin Machine (TM) is a recent automaton-based algorithm for reinforcement learning. It has demonstrated competitive accuracy on many popular benchmarks while providing a natural interpretability. Due to its logically underpinning it is amenable to hardware implementation with faster performance and higher energy efficiency than conventional Artificial Neural Networks (ANNs). This paper provides an overview of Tsetlin Machine architecture and its hyper-parameters as compared to ANN. Furthermore, it gives practical examples of TM application for patterns recognition using MNIST dataset as a case study. In this work we also prove reproducibility of TM learning process to confirm its trustworthiness and convergence in the light of the stochastic nature of TAs reinforcement.
ISSN:2770-4254
DOI:10.1109/IDAACS58523.2023.10348711