When Noise meets Chaos: Stochastic Resonance in Neurochaos Learning

TL;DR

This paper demonstrates the occurrence of stochastic resonance in neurochaos learning, showing that optimal noise levels enhance signal detection and classification performance in brain-inspired models using both simulated and real data.

Contribution

It is the first to connect chaos, noise, and learning in neurochaos models, revealing stochastic resonance as a key mechanism for improved neural computation.

Findings

Stochastic resonance occurs at the single neuron level in neurochaos learning.

Optimal noise levels improve classification accuracy in neurochaos architectures.

SR enhances subthreshold signal detection in brain-inspired AI models.

Abstract

Chaos and Noise are ubiquitous in the Brain. Inspired by the chaotic firing of neurons and the constructive role of noise in neuronal models, we for the first time connect chaos, noise and learning. In this paper, we demonstrate Stochastic Resonance (SR) phenomenon in Neurochaos Learning (NL). SR manifests at the level of a single neuron of NL and enables efficient subthreshold signal detection. Furthermore, SR is shown to occur in single and multiple neuronal NL architecture for classification tasks - both on simulated and real-world spoken digit datasets. Intermediate levels of noise in neurochaos learning enables peak performance in classification tasks thus highlighting the role of SR in AI applications, especially in brain inspired learning architectures.