Does the neuron “learn” like the synapse?
Advances in neural information processing systems 1
Improving the Performance of Feedforward Neural Networks by Noise Injection into Hidden Neurons
Journal of Intelligent and Robotic Systems
On Chaos and Neural Networks: The Backpropagation Paradigm
Artificial Intelligence Review
Chaos and Time-Series Analysis
Chaos and Time-Series Analysis
Distance-Based Sparse Associative Memory Neural Network Algorithm for Pattern Recognition
Neural Processing Letters
CB3: An Adaptive Error Function for Backpropagation Training
Neural Processing Letters
A Hybrid Training Algorithm for Feedforward Neural Networks
Neural Processing Letters
On Weight-Noise-Injection Training
Advances in Neuro-Information Processing
A Novel Weightless Artificial Neural Based Multi-Classifier for Complex Classifications
Neural Processing Letters
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Magnified gradient function with deterministic weight modification in adaptive learning
IEEE Transactions on Neural Networks
Harnessing chaotic activation functions in training neural network
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part II
Convergence of chaos injection-based batch backpropagation algorithm for feedforward neural networks
ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I
Hi-index | 0.00 |
Chaos appears in many natural and artificial systems; accordingly, we propose a method that injects chaos into a supervised feed forward neural network (NN). The chaos is injected simultaneously in the learnable temperature coefficient of the sigmoid activation function and in the weights of the NN. This is functionally different from the idea of noise injection (NI) which is relatively distant from biological realism. We investigate whether chaos injection is more efficient than standard back propagation, adaptive neuron model, and NI algorithms by applying these techniques to different benchmark classification problems such as heart disease, glass, breast cancer, and diabetes identification, and time series prediction. In each case chaos injection is superior to the standard approaches in terms of generalization ability and convergence rate. The performance of the proposed method is also statistically different from that of noise injection.