Stability and discriminative properties of the AMI model

Author

Hoang, D.B. ; James, M.

Author_Institution

Dept. of Comput. Sci., Sydney Univ., NSW, Australia

Volume

1

fYear

1997

fDate

9-12 Jun 1997

Firstpage

270

Abstract

We consider a basic biologically plausible neural circuit that employs supragranular self-gain, negative feedback via inhibitory infragranular neuron. Such circuitry has been used as fundamental building blocks in the AMI (a model of intelligence) modular neural network. We derive the conditions for stability of an adaptive model of such a circuit with nonlinear self-gain and nonlinear adaptation characteristics. We also present the simulation results which demonstrate the discriminative property of the discriminative compartment of an AMI module

Keywords

adaptive systems; associative processing; circuit feedback; circuit stability; learning (artificial intelligence); neural nets; AMI model; adaptive model; associative compartment; atomic intelligent module; discriminative compartment; inhibitory infragranular neuron; learning algorithm; modular neural networks; negative feedback; nonlinear adaptation; nonlinear self-gain; stability; supragranular self-gain; Ambient intelligence; Biological system modeling; Circuit simulation; Circuit stability; Feedback circuits; Intelligent networks; Intelligent structures; Negative feedback; Neural networks; Neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.611677

Filename

611677