Adaptive thresholds for neural networks with synaptic noise

dc.creatorBolle, D.
dc.creatorHeylen, R.
dc.date2007-08-02
dc.date.accessioned2026-07-07T08:21:54Z
dc.date.available2026-07-07T08:21:54Z
dc.descriptionThe 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.
dc.description12 pages, 10 figures
dc.identifierhttps://arxiv.org/abs/0708.0328
dc.identifierhttp://arxiv.org/abs/0708.0328
dc.identifierInternational Journal of Neural Systems, Vol. 17, No. 4 (2007) 241-252
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/135474
dc.subjectDisordered Systems and Neural Networks
dc.subjectStatistical Mechanics
dc.titleAdaptive thresholds for neural networks with synaptic noise
dc.typetext

Files

Collections