Cooperative co-evolution of multilayer perceptrons

Authors:
P. A. Castillo;M. G. Arenas;J. J. Merelo;G. Romero
Affiliations:
Department of Architecture and Computer Technology, University of Granada, Granada, Spain;Department of Architecture and Computer Technology, University of Granada, Granada, Spain;Department of Architecture and Computer Technology, University of Granada, Granada, Spain;Department of Architecture and Computer Technology, University of Granada, Granada, Spain
Venue:
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
Year:
2003

Citing 2
Cited 0

New theorems on global convergence of some dynamical systems

Neural Networks
Attractive Periodic Sets in Discrete-Time Recurrent Networks (with Emphasis on Fixed-Point Stability and Bifurcations in Two-Neuron Networks)

Neural Computation

Quantified Score

Hi-index	0.01

Visualization

Abstract

A theoretical investigation of the dynamics of continuous Hopfield networks, in a modified formulation proposed by Abe, is undertaken. The fixed points are classified according to whether they lie inside or they are vertices of the unit hypercube. It is proved that interior equilibria are saddle points. Besides, a procedure is sketched that determines the basins of attraction of stable vertices. The calculations are completed for the two-neuron network. These results contribute to a solid foundation for these systems, needed for the study of practical problems such as local minima or convergence speed.