Litcius/Paper detail

Systematic Search for Optimal Hyper-parameters of the Tsetlin Machine on MNIST Dataset

Olga Tarasyuk, Tousif Rahman, Rishad Shafik, Alex Yakovlev, Anatoliy Gorbenko, Ole‐Christoffer Granmo, Lei Jiao

202315 citationsDOI

Abstract

Modern Machine Learning (ML) models have a significant number of hyper-parameters that need adjusting to leverage performance and energy efficiency for a given model configuration during training. This becomes a considerable design challenge with increasing complexity requiring larger models. This paper explores the Tsetlin Machine (TM) - a new logic-based ML approach with only four hyper-parameters regardless of the problem space. Two of these hyper-parameters influence the TM architecture while the remaining two impact the learning efficacy. This work focuses on the systematic search for optimal hyper-parameters for the TM and aims to understand how hyper-parameter values affect performance and prediction accuracy using MNIST dataset as a case study.

Topics & Concepts

MNIST databaseComputer scienceArtificial intelligenceMachine learningDeep learningMetaheuristic Optimization Algorithms ResearchFuzzy Logic and Control SystemsMachine Learning and Algorithms