Grossberg network

Grossberg network is an artificial neural network introduced by Stephen Grossberg. It is a self organizing, competitive network based on continuous time.^[1] Grossberg, a neuroscientist and a biomedical engineer, designed this network based on the human visual system.

Shunting model[edit]

The shunting model is one of Grossberg's neural network models, based on a Leaky integrator, described by the differential equation

{dn \over dt}\;=\;-An\;+(B-n)E\;-(C+n)I

,

where $n=n(t)$ represents the activation level of a neuron, $E=E(t)$ and $I=I(t)$ represent the excitatory and inhibitory inputs to the neuron, and $A$ , $B$ , and $C$ are constants representing the leaky decay rate and the maximum and minimum activation levels.

At equilibrium (where $dn/dt=0$ ), the activation $n$ reaches the value

n\;=\;{BE-CI \over A+E+I}

.

References[edit]

^ Martin T. Hagan; Howard B. Demuth; Mark H. Beale (January 2002) [1996]. "Chapter 15: Grossberg Network". Neural Network Design (1st ed.). PWS Publishing Co. pp. 15–1. ISBN 978-0971732100.

[Hagan-1] Martin T. Hagan; Howard B. Demuth; Mark H. Beale (January 2002) [1996]. "Chapter 15: Grossberg Network". Neural Network Design (1st ed.). PWS Publishing Co. pp. 15–1. ISBN 978-0971732100.

[1]