ePrints

An Alternate Feedback Mechanism for Tsetlin Machines on Parallel Architectures

Lookup NU author(s): Dr Jordan Morris, Dr Ashur Rafiev, Dr Fei Xia, Professor Rishad ShafikORCiD, Professor Alex YakovlevORCiD

Downloads

• Accepted version [.pdf]

Licence

This is the authors' accepted manuscript of a conference proceedings (inc. abstract) published in its final definitive form in 2022. For re-use rights please refer to the publishers terms and conditions.

Abstract

This work proposes an alternative feedback mechanism for the Tsetlin Machine, a nascent machine learning algorithm that accepts binarized input data and uses propositional logic to identify and accumulate sub-patterns from a given entropy. The proposed method monitors and limits the included literals that contribute to the sub-patterns. This permits the algorithm to converge without requiring the class sum, the primary hurdle of a fully parallelized implementation. Empirical results from a custom RISC-V NoC cluster demonstrate up to a 36X reduction in wall-clock runtime for a 2.5% reduction in accuracy using the MNIST dataset. The proposed method outperforms the original feedback mechanism by 2% when the number of accumulated sub-patterns (clauses) are tightly constrained for the same dataset. This is achieved with a 1.8X reduction in wall-clock runtime.

Publication metadata

Author(s): Morris J, Rafiev A, Xia F, Shafik R, Yakovlev A, Brown A

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: International Symposium on the Tsetlin Machine

Year of Conference: 2022

Online publication date: 21/06/2022

Acceptance date: 17/05/2022

Date deposited: 28/06/2022

URL: https://www.aconf.org/conf_182418.html

ePrints DOI: 10.57711/tjk7-5s43

Share