A note on chaotic behavior in simple neural networks
Neural Networks
Introduction to the theory of neural computation
Introduction to the theory of neural computation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
An introduction to neural computing
An introduction to neural computing
| Hi-index | 0.00 |
In this paper, we investigate the impact of chaos on the learningprocess of the XOR-boolean function by backpropagation neural networks. Ithas been shown previously that such networks exhibit chaotic behavior butit has never been studied whether chaos enhances or prohibits learning. Weshow that chaos (when learning the XOR-boolean function) does indeed allowlearning but our findings do not indicate any positive role of chaos forlearning. In particular, we found that the temperature parameter in thebackpropagation algorithm causes the parameter regime, as represented by means of a bifurcation diagram, to shift to the right. We furthermore foundthat as less chaos appears during the learning process, the faster, on theaverage, a neural network learned the XOR-function.