# [Benchmarking CIFAR-10 with Tsetlin Machines](https://www.literal-labs.ai/tsetlin-machines/cifar-10-benchmarks.html)

## Accuracy reaching 82.8%

**Authors**: include Ylva Grønningsæter, Halvor S. Smørvik, [Ole-Christoffer Granmo](https://www.literal-labs.ai/about/ole-christoffer-granmo.html)  
**Published**: 2024, _arxiv_

### Summary

This paper presents an optimised toolbox for image classification using [Tsetlin Machines](https://www.literal-labs.ai/tsetlin-machines/) on the CIFAR-10 dataset, achieving a significant leap in accuracy. Tsetlin Machines, known for their energy efficiency and interpretability, have traditionally lagged in handling complex colour images like those in CIFAR-10. By integrating novel Tsetlin Machine Specialists and advanced image processing techniques, such as Canny edge detection, Histogram of Oriented Gradients, adaptive thresholding methods, and colour thermometers, this research enhances the Tsetlin Machines' performance.

A rigorous hyperparameter search yielded optimal configurations for these specialists, culminating in a new state-of-the-art TM accuracy of 82.8% on CIFAR-10. The paper highlights the scalability of the proposed TM Composites architecture, which allows multiple independently trained Tsetlin Machines to collaborate, effectively pooling their strengths to outperform previous benchmarks.

The study underscores the potential of Tsetlin Machines in image analysis, offering an alternative to deep learning models with fewer computational resources and better interpretability. This toolbox sets a new benchmark for using Tsetlin Machines on CIFAR-10, making it a foundation for future research into energy-efficient, interpretable machine learning models. Keywords: CIFAR-10, Tsetlin Machines, image processing, benchmarking, machine learning.

### Read more

The full paper _An Optimised Toolbox for Advanced Image Processing with Tsetlin Machine Composites_ is available from [arxiv](https://arxiv.org/abs/2406.00704).

### Article

First published by arxiv on 2 Jun 2024.

DOI: arXiv:2406.00704

### Other research by our team

**[MATADOR: Automated System-on-Chip Tsetlin Machine Design Generation for Edge Applications](https://www.literal-labs.ai/research/tsetlin-machine-system-on-chip.html)**

[](https://www.literal-labs.ai/research/tsetlin-machine-system-on-chip.html)

**[REDRESS: Generating Compressed Models for Edge Inference Using Tsetlin Machines](https://www.literal-labs.ai/research/compress-tsetlin-machine-automata.html)**

[](https://www.literal-labs.ai/research/compress-tsetlin-machine-automata.html)

**[Systematic Search for Optimal Hyper parameters of the Tsetlin Machine on MNIST Dataset](https://www.literal-labs.ai/research/optimise-hyperparameters-tsetlin-machine-mnist.html)**

[](https://www.literal-labs.ai/research/optimise-hyperparameters-tsetlin-machine-mnist.html)

**[Visualization of Machine Learning Dynamics in Tsetlin Machines](https://www.literal-labs.ai/research/tsetlin-machine-visualisation.html)**

[](https://www.literal-labs.ai/research/tsetlin-machine-visualisation.html)

**[Self-timed reinforcement learning using Tsetlin Machine](https://www.literal-labs.ai/research/tsetlin-machine-reinforcement-learning.html)**

[](https://www.literal-labs.ai/research/tsetlin-machine-reinforcement-learning.html)

**[Learning automata based energy-efficient AI hardware design for IoT applications](https://www.literal-labs.ai/research/royal-society-ai-automata.html)**

[](https://www.literal-labs.ai/research/royal-society-ai-automata.html)