start10 - %LEARNING_CONSTANT=0.1 %w_CONSTANT=5; % % %step2...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
%start10.m R=10; N=100; P=100; d=ones(R,N/R); d=d*-1; d(1,:)=1; %C=fix(10*rand(3,2)); %a=ones(10,100); for n=2:R a=ones(R,N/R); a=a*-1; a(n,:)=1; d=horzcat(d,a); end % %step1 %LEARNING_CONSTANT=0.01 %LEARNING_CONSTANT=0.1 %LEARNING_CONSTANT=0.1
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: %LEARNING_CONSTANT=0.1 %w_CONSTANT=5; % % %step2 % %With threshold weight, extended weight matrices if negative==-1 W=(2*W_CONSTANT*rand(R,N+1))-W_CONSTANT; else W=W_CONSTANT*rand(R,N+1); end %...
View Full Document

This note was uploaded on 07/13/2011 for the course ECE 501 taught by Professor Deniz during the Spring '11 term at Istanbul Universitesi.

Ask a homework question - tutors are online