Tsetlin Machine-Based Image Classification FPGA Accelerator With On-Device Training
IEEE Transactions on Circuits and Systems I: Regular Papers · 2025-02 · 72 (2) · 830-843
DOI: 10.1109/tcsi.2024.3519191 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems I: Regular Papers, 2025-02. Verfasst von Svein Anders Tunheim und 4 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: University of Agder, Norway.
Abstract (Originalsprache)
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 $28\times 28$ 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~\mu $ 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.
Förderung
- University of Agder, Norway
Zitieren
APA
Tunheim, S. A., Jiao, L., Shafik, R., Yakovlev, A., & Granmo, O. (2025). Tsetlin Machine-Based Image Classification FPGA Accelerator With On-Device Training. IEEE Transactions on Circuits and Systems I: Regular Papers, 72(2), 830-843. https://doi.org/10.1109/tcsi.2024.3519191
Vancouver
Tunheim SA, Jiao L, Shafik R, Yakovlev A, Granmo O. Tsetlin Machine-Based Image Classification FPGA Accelerator With On-Device Training. IEEE Transactions on Circuits and Systems I: Regular Papers. 2025;72(2):830-843. doi:10.1109/tcsi.2024.3519191
BibTeX
@article{Tunheim2025,
author = {Tunheim, Svein Anders and Jiao, Lei and Shafik, Rishad and Yakovlev, Alex and Granmo, Ole-Christoffer},
title = {Tsetlin Machine-Based Image Classification FPGA Accelerator With On-Device Training},
journal = {IEEE Transactions on Circuits and Systems I: Regular Papers},
year = {2025},
volume = {72},
number = {2},
pages = {830--843},
doi = {10.1109/tcsi.2024.3519191}
}
EUVIMED