Hyperparameter-Free Neurochaos Learning Algorithm for Classification
This work addresses the scalability and efficiency issues in brain-inspired classification for real-world tasks, though it is incremental as it builds on the existing Neurochaos Learning framework.
The authors tackled the problem of hyperparameter tuning and computational complexity in Neurochaos Learning by proposing AutochaosNet, a hyperparameter-free variant that eliminates training and parameter optimization, achieving competitive or superior classification performance with significantly reduced training time.
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.