Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size

TL;DR

This paper introduces Clause Size Constrained Tsetlin Machines (CSC-TMs), a variant that limits clause size to improve interpretability and reduce power consumption while maintaining high accuracy across diverse tasks.

Contribution

The paper proposes a novel TM variant with soft clause size constraints, demonstrating improved interpretability and efficiency without sacrificing accuracy.

Findings

CSC-TMs achieve up to 80 times fewer literals while maintaining accuracy.

Shorter clauses improve accuracy on datasets like TREC, IMDb, BBC Sports.

Power consumption analysis shows reduced energy use with CSC-TMs.

Abstract

Tsetlin machine (TM) is a logic-based machine learning approach with the crucial advantages of being transparent and hardware-friendly. While TMs match or surpass deep learning accuracy for an increasing number of applications, large clause pools tend to produce clauses with many literals (long clauses). As such, they become less interpretable. Further, longer clauses increase the switching activity of the clause logic in hardware, consuming more power. This paper introduces a novel variant of TM learning - Clause Size Constrained TMs (CSC-TMs) - where one can set a soft constraint on the clause size. As soon as a clause includes more literals than the constraint allows, it starts expelling literals. Accordingly, oversized clauses only appear transiently. To evaluate CSC-TM, we conduct classification, clustering, and regression experiments on tabular data, natural language text, images, and board games. Our results show that CSC-TM maintains accuracy with up to 80 times fewer literals. Indeed, the accuracy increases with shorter clauses for TREC, IMDb, and BBC Sports. After the accuracy peaks, it drops gracefully as the clause size approaches a single literal. We finally analyze CSC-TM power consumption and derive new convergence properties.