Dynamic neural unit and function approximation

Author

Rao, D.H. ; Gupta, M.M.

Author_Institution

Intelligent Syst. Res. Lab., Saskatchewan Univ., Saskatoon, Sask., Canada

fYear

1993

fDate

1993

Firstpage

743

Abstract

A dynamic model of a neuron for applications in robotics and control is developed. The proposed model, called the dynamic neural unit (DNU), comprises two distinct operations: the synaptic operation, which determines the optimum feedforward and feedback synaptic weights controlling the dynamics of the neuron; and the somatic operation, which determines the optimum gain of the nonlinear activation function for a given task. The function approximation capability of the network of DNUs is described by considering linear and trigonometric operators. Computer simulation results are presented

Keywords

computerised control; function approximation; neural nets; robots; DNU; dynamic neural unit; feedback synaptic weights; function approximation; linear operators; nonlinear activation function; optimum feedforward synaptic weights; somatic operation; synaptic operation; trigonometric operators; Artificial neural networks; Biological neural networks; Biological system modeling; Central nervous system; Circuits; Function approximation; Intelligent robots; Neurofeedback; Neurons; Output feedback;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1993., IEEE International Conference on

Conference_Location

San Francisco, CA

Print_ISBN

0-7803-0999-5

Type

conf

DOI

10.1109/ICNN.1993.298648

Filename

298648