Genetic Algorithm Based Techniques For Determining Weights In A Back Propagation Network
Description:-Genetic algorithms work with population of individual strings.
The steps involved in GAs are:
− Each individual string represents a possible solution of the problem considered,
− Each individual string is assigned a fitness value,
− High fit individuals participate in reproduction, yields new strings as offspring and they share some features with each parents,
− Low fit individuals are kept out from reproduction and so die,
− A whole new population of possible solutions to the problem is generated by selecting high fit individuals from current generation,
− This new generation contains characteristics which are better than their ancestors,
− processing this way after many generations, the entire population inherits the best and fit solution.
However, before a GA is executed :
− A suitable coding for the problem is devised,
− A fitness function is formulated,
− Parents have to be selected for reproduction and crossover to generate offspring.
Coding
Assume a BPN configuration ℓ - m – n where
− ℓ is input, m is hidden and n is output neurons.
− Number of weights to be determined is (ℓ n) m.
− Each weight (gene) is a real number.
− assume number of digits (gene length) in weight are d .
− a string S represents weight matrices of input-hidden and the hidden output layers in a linear form arranged as row-major or column-major selected.
− Population size is the randomly generated initial population of p chromosomes.
Weight Extraction
Extract weights from each chromosome, later to determine the fitness values.
Let x1,x2 . . . x d , . . . . x L represent a chromosome and Let xkd 1 , xkd 2 , . . x(k 1)d represent kth gene (k ≥ 0) in the chromosomes.
The actual weight wk is given by
