Drexel dragonThe Math ForumDonate to the Math Forum



Search All of the Math Forum:

Views expressed in these public forums are not endorsed by Drexel University or The Math Forum.


Math Forum » Discussions » Software » comp.soft-sys.matlab

Topic: A neural network question
Replies: 0  

Advanced Search

Back to Topic List Back to Topic List  
Tom Miller

Posts: 3
Registered: 12/7/04
A neural network question
Posted: Jun 18, 1996 11:57 AM
  Click to see the message monospaced in plain text Plain Text   Click to reply to this topic Reply

Hi there,
I'm hoping someone with the neural networks toolbox (and a
little more knowledge than me) can answer a few questions.

1) the neural netork toolbox manual says that the trainwh
function uses the "Widrow Hoff" learning algorithm. I cant
find any direct references to that in Widrow's "Adaptive
signal processing" book. Is the Widrow Hoff LR the same as
the Least Mean Squares algorithm?

2) The trainwh function returns a bias value. The lms algorithm
doesn't address adjustment of the bias input - what rule does
this function use for bias adjustment?

3) The lms algorithm is supposed to "jitter about"
when it gets close to the minimum error (i.e. the best set of
synaptic weights) when I run the training algorithm I get what
appears to be an exponential decrease in the error function
over time - this is good but it doesn't mesh with the
description of the LMS algorithm given in the literature.

Can anyone out there explain? I would really appreciate the help.

Tom Miller





Point your RSS reader here for a feed of the latest messages in this topic.

[Privacy Policy] [Terms of Use]

© Drexel University 1994-2014. All Rights Reserved.
The Math Forum is a research and educational enterprise of the Drexel University School of Education.