# An All-digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification Accelerator

Source: [An All-digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification Accelerator](<https://www.sota2.com/research/paper/68fa7a0d1e209131cea80d0b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:11:23.415Z

Authors: Svein Anders Tunheim, Yujin Zheng, Lei Jiao, Rishad Shafik, Alex Yakovlev, Ole-Christoffer Granmo

Published: 2025-01-31T17:51:46.000Z

## Abstract

We present an all-digital programmable machine learning accelerator chip for image classification, underpinning on the Tsetlin machine (TM) principles. The TM is an emerging machine learning algorithm founded on propositional logic, utilizing sub-pattern recognition expressions called clauses. The accelerator implements the coalesced TM version with convolution, and classifies booleanized images of 28$\\times$28 pixels with 10 categories. A configuration with 128 clauses is used in a highly parallel architecture. Fast clause evaluation is achieved by keeping all clause weights and Tsetlin automata (TA) action signals in registers. The chip is implemented in a 65 nm low-leakage CMOS technology, and occupies an active area of 2.7 mm$^2$. At a clock frequency of 27.8 MHz, the accelerator achieves 60.3k classifications per second, and consumes 8.6 nJ per classification. This demonstrates the energy-efficiency of the TM, which was the main motivation for developing this chip. The latency for classifying a single image is 25.4 $\\mu$s which includes system timing overhead. The accelerator achieves 97.42%, 84.54% and 82.55% test accuracies for the datasets MNIST, Fashion-MNIST and Kuzushiji-MNIST, respectively, matching the TM software models.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on MNIST (Accuracy and Hardware Efficiency Metrics)](<https://www.sota2.com/research/sota/image-classification-on-mnist-accuracy-and-hardware-efficiency-metrics.md>): Image Classification; MNIST; Accuracy: 97.42.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2501.19347>)

[PDF](<https://arxiv.org/pdf/2501.19347.pdf>)