Description and training of neural network dynamics


Attractor properties of a popular discrete-time neural network model are illustrated through numerical simulations. The most complex dynamics is found to occur within particular ranges of parameters controlling the symmetry and magnitude of the weight matrix. A small network model is observed to produce fixed points, limit cycles, mode-locking, the Ruelle-Takens route to chaos, and the period-doubling route to chaos. Training algorithms for tuning this dynamical behaviour are discussed. Training can be an easy or difficult task, depending whether the problem requires the use of temporal information distributed over long time intervals. Such problems require training algorithms which can handle hidden nodes. The most prominent of these algorithms, back propagation through time, solves the temporal credit assignment problem in a way which can work only if the relevant information is distributed locally in time. The Moving Targets algorithm works for the more general case, but is computationally intensive, and prone to local minima.

Divisions: Aston University (General)
Event Title: Neurodynamics, Proceedings of the 9th Summer Workshop
Event Type: Other
Event Dates: 1991-01-01 - 1991-01-01
Uncontrolled Keywords: popular discrete-time neural,network model,simulations,weight matrix,algorithms,dynamical behaviour,temporal information,temporal credit assignment
PURE Output Type: Paper
Published Date: 1991
Authors: Rohwer, Richard


Export / Share Citation


Additional statistics for this record