Title :
Obtaining optimum minimum points of error functions: a neural network approach
Author_Institution :
Dept. of Electr. & Electron. Eng., Pretoria Univ., South Africa
fDate :
11/1/1995 12:00:00 AM
Abstract :
An iterative neural network solution for the problem of obtaining the optimal minima of error or cost functions containing many local minima is proposed. Use is made of an adaptive constraint function eliminating local minima previously encountered. It is shown that the method yields very fast response times, and the method is applied to a representative example with simulation results verifying its usefulness and speed
Keywords :
constraint handling; iterative methods; neural nets; nonlinear programming; signal processing; adaptive constraint function; analogue neural network; cost functions; error functions; iterative neural network solution; local minima; optimum minimum points; response times; simulation results; Adaptive signal processing; Circuits; Control theory; Cost function; Delay; Error correction; Iterative methods; Neural networks; Process control; Signal processing algorithms;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on
