Loading...
Please wait, while we are loading the content...
Similar Documents
The roles of stability and symmetry in the dynamics of neural networks (1988).
| Content Provider | CiteSeerX |
|---|---|
| Author | Krautht, Werner Nadalf, Jean-Pierre Mczardej, Marc |
| Abstract | Abstract. In this paper we study the retrieval phase of spin-glass-like neural networks. Considering that the dynamics should depend only on gauge-invariant quantities, we propose that two such parameters, characterising the symmetry of the neural net’s connec-tions and the stabilities of the patterns, are responsible for most of the dynamical effects. This is supported by a numerical study of the shape of the basins of attraction for a one-pattern neural network (OPN) model. The effects of stability and symmetry on the short-time dynamics of this model are studied analytically, and the full dynamics for vanishing symmetry is shown to be exactly solvable. 1. |
| File Format | |
| Publisher Date | 1988-01-01 |
| Access Restriction | Open |
| Subject Keyword | Neural Network Full Dynamic Gauge-invariant Quantity Dynamical Effect Numerical Study One-pattern Neural Network Neural Net Connec-tions Short-time Dynamic Retrieval Phase Spin-glass-like Neural Network |
| Content Type | Text |
| Resource Type | Article |
