MATLAB Answers

0

Can neural net weights be negative?

Asked by Michael on 21 Jul 2014
Latest activity Answered by Michael on 21 Jul 2014
I have a question on neural net weights. My understanding is that the default is they add up to one. Can they be negative? (If they can't be negative, it seems to me I would need to make sure to make input data generally proportional to the target output. If they can be negative, then I can just let the system adapt to the proportionality.) Thanks!

  0 Comments

Sign in to comment.

2 Answers

Answer by Shashank Prasanna on 21 Jul 2014
 Accepted Answer

Weights can be whatever the training algorithm determines the weights to be. If you take the simple case of a perceptron (1 layer NN), the weights are the slope of the separating (hyper)plane, it could be positive or negative.
Take a look at some examples in the neural network toolbox:

  0 Comments

Sign in to comment.


Answer by Michael on 21 Jul 2014

Thanks Shashank, I'll check it out.

  0 Comments

Sign in to comment.