Nonlinear neural networks. II. Information processing |
| |
Authors: | J L van Hemmen D Grensing A Huber R Kühn |
| |
Institution: | (1) Present address: Universität Heidelberg, Sonderforschungsbereich 123, D-6900 Heidelberg, West Germany;(2) Institut für Theoretische Physik und Sternwarte der Universität Kiel, D-2300 Kiel, West Germany |
| |
Abstract: | Information processing in nonlinear neural networks with a finite numberq of stored patterns is studied. Each network is characterized completely by its synaptic kernelQ. At low temperatures, the nonlinearity typically results in 2q–2–q metastable, pure states in addition to theq retrieval states that are associated with theq stored patterns. These spurious states start appearing at a temperature
, which depends onq. We give sufficient conditions to guarantee that the retrieval states bifurcate first at a critical temperatureT
c
and that
/T
c
0 asq. Hence, there is a large temperature range whereonly the retrieval states and certain symmetric mixtures thereof exist. The latter are unstable, as they appear atT
c
. For clipped synapses, the bifurcation and stability structure is analyzed in detail and shown to approach that of the (linear) Hopfield model asq. We also investigate memories that forget and indicate how forgetfulness can be explained in terms of the eigenvalue spectrum of the synaptic kernelQ. |
| |
Keywords: | Nonlinear neural networks bifurcation and stability information processing logical operations forgetfulness |
本文献已被 SpringerLink 等数据库收录! |
|