ChaosNet: A Chaos based Artificial Neural Network Architecture for Classification
This work addresses classification problems for machine learning practitioners by offering a robust architecture that performs well with very limited training data, though it appears incremental as it builds on existing chaotic map properties.
The authors tackled classification tasks by proposing ChaosNet, a novel chaos-based artificial neural network architecture inspired by chaotic neuron firing, which achieved performance accuracies ranging from 73.89% to 98.33% with as few as 7 training samples per class.
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.