Exploring Effects of Hyperdimensional Vectors for Tsetlin Machines

TL;DR

This paper introduces a hypervector-based approach to enhance Tsetlin machines, enabling them to handle complex data types more effectively, leading to improved accuracy and learning speed across various benchmarks.

Contribution

It proposes a novel hypervector encoding method for Tsetlin machines, significantly expanding their capacity and flexibility for complex data structures.

Findings

Higher accuracy on benchmark datasets

Faster learning compared to traditional TMs

Effective encoding of images, chemical compounds, and text

Abstract

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.