On Mon, Jun 15, 2009 at 5:00 PM, Trin Trin <[email protected]> wrote:

> Hi Alp,
> - even with correctly programmed back-propagation, it is usually hard to
> make the net converge.
>

Yeah, I know, that's why we're training it until the quadratic error goes
under 0.1.


> - usually you initialize neuron weights with somewhat random values, when
> working with back-propagation.
>

Yeah, that'll be done too, once the algorithm will be ready. I'll provide
fancy and easy functions to create a neural net just giving the numbers of
layers and their sizes.


> - do some debug prints of the net error while training to see how it is
> going
>

Good idea, yeah.


> - xor function cannot be trained with a single layer neural net !!!
>

That's why there are 2 layers there, one hidden and the output one. I
consider the "inputs" as ... inputs, not as a first layer of the NN.

Thanls for your time. If you have any clues when reading the code, don't
hesitate of course.

-- 
Alp Mestan
http://blog.mestan.fr/
http://alp.developpez.com/
_______________________________________________
Haskell-Cafe mailing list
[email protected]
http://www.haskell.org/mailman/listinfo/haskell-cafe

Reply via email to