Chaotic Dynamics in Iterated Map Neural Networks with Piecewise Linear Activation Function
Abstract
Description
The paper examines the discrete-time dynamics of neuron models (of excitatory and inhibitory types) with piecewise linear activation functions, which are connected in a network. The properties of a pair of neurons (one excitatory and the other inhibitory) connected with each other, is studied in detail. Even such a simple system shows a rich variety of behavior, including high-period oscillations and chaos. Border-collision bifurcations and multifractal fragmentation of the phase space is also observed for a range of parameter values. Extension of the model to a larger number of neurons is suggested under certain restrictive assumptions, which makes the resultant network dynamics effectively one-dimensional. Possible applications of the network for information processing are outlined. These include using the network for auto-association, pattern classification, nonlinear function approximation and periodic sequence generation.
20 pages, using fuin.cls (included). 12 figures. To appear in Fundamenta Informaticae (1999)
20 pages, using fuin.cls (included). 12 figures. To appear in Fundamenta Informaticae (1999)