Neural Network Toolbox weighting value

How to define weighting value manually in matlab neural network toolbox?

Thanks

Answer 1

[Greg Heath]

Typically, all of the functions are automatically intialized with random intial weights in train or configure. A major exception is newrb which chooses the training vector with the highest error on a linear classifier (H=0).

See some of my designs by searching on

greg configure

Note that you must use configure before train when designing multiple nets in a loop.

Hope this helps.

Thank you for formally accepting my answer

Greg

[Mohamad Aulady]

Can you give some link to find your some design (greg configure)

Thanks for helping me

[Greg Heath]

You can search on

greg configure

just as well as me.

Greg

Answer 2

[Greg Heath]

Is this what you mean

y = B2 + LW*tanh(B1+IW*x)

?

[Mohamad Aulady]

i means the initial value of IW and LW, how we can define it manually?