Adaptive thresholds for neural networks with synaptic noise
Disordered Systems and Neural Networks
2007-08-03 v1 Statistical Mechanics
Abstract
The inclusion of a macroscopic adaptive threshold is studied for the retrieval dynamics of both layered feedforward and fully connected neural network models with synaptic noise. These two types of architectures require a different method to be solved numerically. In both cases it is shown that, if the threshold is chosen appropriately as a function of the cross-talk noise and of the activity of the stored patterns, adapting itself automatically in the course of the recall process, an autonomous functioning of the network is guaranteed. This self-control mechanism considerably improves the quality of retrieval, in particular the storage capacity, the basins of attraction and the mutual information content.
Cite
@article{arxiv.0708.0328,
title = {Adaptive thresholds for neural networks with synaptic noise},
author = {D. Bolle and R. Heylen},
journal= {arXiv preprint arXiv:0708.0328},
year = {2007}
}
Comments
12 pages, 10 figures