Hyperparameter-Free Neurochaos Learning Algorithm for Classification

TL;DR

AutochaosNet is a hyperparameter-free, brain-inspired classification algorithm that simplifies neurochaos learning by eliminating training and tuning, while maintaining or improving performance.

Contribution

It introduces AutochaosNet, a novel hyperparameter-free variant of neurochaos learning that reduces computational effort and training time, with competitive classification accuracy.

Findings

AutochaosNet achieves comparable or better accuracy than ChaosNet.

It significantly reduces training time and computational effort.

Exhibits strong generalization capabilities.

Abstract

Neurochaos Learning (NL) is a brain-inspired classification framework that employs chaotic dynamics to extract features from input data and yields state of the art performance on classification tasks. However, NL requires the tuning of multiple hyperparameters and computing of four chaotic features per input sample. In this paper, we propose AutochaosNet - a novel, hyperparameter-free variant of the NL algorithm that eliminates the need for both training and parameter optimization. AutochaosNet leverages a universal chaotic sequence derived from the Champernowne constant and uses the input stimulus to define firing time bounds for feature extraction. Two simplified variants - TM AutochaosNet and TM-FR AutochaosNet - are evaluated against the existing NL architecture - ChaosNet. Our results demonstrate that AutochaosNet achieves competitive or superior classification performance while significantly reducing training time due to reduced computational effort. In addition to eliminating training and hyperparameter tuning, AutochaosNet exhibits excellent generalisation capabilities, making it a scalable and efficient choice for real-world classification tasks. Future work will focus on identifying universal orbits under various chaotic maps and incorporating them into the NL framework to further enhance performance.