ChaosNet: A Chaos based Artificial Neural Network Architecture for Classification

TL;DR

ChaosNet is a novel neural network architecture inspired by chaotic neuron firing, utilizing chaotic maps for classification tasks, especially effective with very limited training data, and demonstrating robustness to noise.

Contribution

Introduces ChaosNet, a new chaos-based neural network architecture with a unique learning algorithm exploiting topological transitivity for classification.

Findings

Achieves 73.89% - 98.33% accuracy with fewer than 7 training samples per class

Demonstrates robustness to additive parameter noise

Provides an example of a 2-layer ChaosNet improving classification accuracy

Abstract

Inspired by chaotic firing of neurons in the brain, we propose ChaosNet -- a novel chaos based artificial neural network architecture for classification tasks. ChaosNet is built using layers of neurons, each of which is a 1D chaotic map known as the Generalized Luroth Series (GLS) which has been shown in earlier works to possess very useful properties for compression, cryptography and for computing XOR and other logical operations. In this work, we design a novel learning algorithm on ChaosNet that exploits the topological transitivity property of the chaotic GLS neurons. The proposed learning algorithm gives consistently good performance accuracy in a number of classification tasks on well known publicly available datasets with very limited training samples. Even with as low as 7 (or fewer) training samples/class (which accounts for less than 0.05% of the total available data), ChaosNet yields performance accuracies in the range 73.89 % - 98.33 %. We demonstrate the robustness of ChaosNet to additive parameter noise and also provide an example implementation of a 2-layer ChaosNet for enhancing classification accuracy. We envisage the development of several other novel learning algorithms on ChaosNet in the near future.