ePrints

Tsetlin Machine-Based Image Classification FPGA Accelerator With On-Device Training

Lookup NU author(s): Svein Tunheim, Professor Rishad ShafikORCiD, Professor Alex YakovlevORCiD

Downloads

• Accepted version [.pdf]

Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).

Abstract

© IEEE. The Tsetlin Machine (TM) is a novel machine learning algorithm that uses Tsetlin automata (TAs) to define propositional logic expressions (clauses) for classification. This paper describes a field-programmable gate array (FPGA) accelerator for image classification based on the Convolutional Coalesced Tsetlin Machine. The accelerator classifies booleanized images of 28× 28 pixels into 10 classes, and is configured with 128 clauses in a highly parallel architecture. To achieve fast clause evaluation and class prediction, the TA action signals and the clause weights per class are available from registers. Full on-device training is included, and the TAs are implemented with 34 Block RAM (BRAM) instances which operate in parallel. Each BRAM is addressed by the clause number and has a 72-bit word width that supports 8 TAs. The design is implemented in a Xilinx Zynq Ultrascale + XCZU7 FPGA. Running at 50 MHz, the accelerator core achieves 134k image classifications per second, with an energy consumption per classification of 13.3 μ J. A single training epoch of 60k samples requires a processing time of 1.5 seconds. The accelerator obtains a test accuracy of 97.6% on MNIST, 84.1% on Fashion-MNIST and 82.8% on Kuzushiji-MNIST.

Publication metadata

Author(s): Tunheim SA, Jiao L, Shafik R, Yakovlev A, Granmo O-C

Publication type: Article

Publication status: Published

Journal: IEEE Transactions on Circuits and Systems I: Regular Papers

Year: 2025

Volume: 72

Issue: 2

Pages: 830-843

Print publication date: 01/02/2025

Online publication date: 23/12/2024

Acceptance date: 12/12/2024

Date deposited: 16/01/2025

ISSN (print): 1549-8328

ISSN (electronic): 1558-0806

Publisher: IEEE

URL: https://doi.org/10.1109/TCSI.2024.3519191

DOI: 10.1109/TCSI.2024.3519191

ePrints DOI: 10.57711/6zp6-hh49

Altmetrics

Share