File Exchange

image thumbnail

Delta Learning, Widrow Hoff Learning

version 1.0.0.0 (57.5 KB) by Bhartendu
Delta Learning rule, Widrow-Hoff Learning rule (Artificial Neural Networks)

1 Download

Updated 22 May 2017

View License

When comparing with the network output with desired output, if there is error the weight vector w(k) associated with the ith processing unit at the time instant k is corrected (adjusted) as
w(k+1) = w(k) + D[w(k)]
where, D[w(k)] is the change in the weight vector and will be explicitly given for various learning rules.
Delta Learning rule is given by:
w(k+1) = w(k) + eta*[ d(k) - f{ w'(k)*x(k) } ] *f'{ w'(k)*x(k) } *x(k)

Widrow-Hoff Learning rule is given by:

w(k+1) = w(k) + eta*[ d(k) - w'(k)*x(k) ] *x(k)
here: f{ w'(k)*x(k) } = w'(k)*x(k)

Reference:
http://www.ent.mrt.ac.lk/~ekulasek/ami/PartC.pdf

Comments and Ratings (2)

MATLAB Release Compatibility
Created with R2016a
Compatible with any release
Platform Compatibility
Windows macOS Linux