Chaotic dynamics in iterated map neutral networks with piecewise linear activation function

• Autorzy: Sinha S.
• Języki publikacji: EN

Abstrakty

EN

The paper examines the discrete-time dynamics of neuron models (of excitatory and inhibi-tory types) with piecewise linear activation functions, which are connected in a network. The properties of a pair 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, includ-ing 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 applica-tions 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.

Słowa kluczowe

EN

excitatory-inhibitory neutral networks; chaos; nonlinear dynamics

• Wydawca: Polskie Towarzystwo Matematyczne
• Czasopismo: Fundamenta Informaticae
• Rocznik: 1999
• Tom: Vol. 37, Nr 1,2
• Strony: 31--50
• Opis fizyczny: bibliogr. 20 poz.

Twórcy

autor

Sinha S.

• Department of Physica, Indian Institute of Science, Bangalore 560 012, India,