Principles and practice of information theory
Principles and practice of information theory
Adaptive thresholds for layered neural networks with synaptic noise
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Hi-index | 0.00 |
The macroscopic dynamics of an extremely diluted threestate neural network based on mutual information and mean-field theory arguments is studied in order to establish the stability of the stationary states. Results are presented in terms of the pattern-recognition overlap, the neural activity, and the activity-overlap. It is shown that the presence of synaptic noise is essential for the stability of states that recognize only the active patterns when the full structure of the patterns is not recognizable. Basins of attraction of considerable size are obtained in all cases for a not too large storage ratio of patterns.