Chaosnet: a chaos based artificial neural network architecture for classification
From MaRDI portal
Publication:5205680
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.
Recommendations
- scientific article; zbMATH DE number 14852
- Annealed chaotic neural network with nonlinear self-feedback and its application to clustering problem
- Learning-induced pattern classification in a chaotic neural network
- Robust chaos in neural networks
- Neural networks and chaos: construction, evaluation of chaotic networks, and prediction of chaos with multilayer feedforward networks
Cites work
- scientific article; zbMATH DE number 1789350 (Why is no real title available?)
- A chaotic model of sustaining attention problem in attention deficit disorder
- Approximation by superpositions of a sigmoidal function
- Bifurcations, burstings, chaos and crises in the Rose-Hindmarsh model for neuronal activity
- Chaos
- Chaotic dynamics of information processing: The magic number sevel plus- minus two revisited
- Clustering, coding, switching, hierarchical ordering, and control in a network of chaotic elements
- Nearest neighbor pattern classification
- On the information bottleneck theory of deep learning
- Scikit-learn: machine learning in Python
- Using chaotic artificial neural networks to model memory in the brain
Cited in
(7)- scientific article; zbMATH DE number 14852 (Why is no real title available?)
- New 4D and 3D models of chaotic systems developed from the dynamic behavior of nuclear reactors
- scientific article; zbMATH DE number 1854000 (Why is no real title available?)
- Neural networks and chaos: construction, evaluation of chaotic networks, and prediction of chaos with multilayer feedforward networks
- When noise meets chaos: stochastic resonance in neurochaos learning
- Multistable dynamics and control of a new 4D memristive chaotic Sprott B system
- Stimulus classification using chimera-like states in a spiking neural network
This page was built for publication: Chaosnet: a chaos based artificial neural network architecture for classification
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5205680)
