Hi guys,

I'm trying to use a genetic algorithm to train a recurrent neural network. I kind of understand what bias nodes are for in feed forward networks. Do I need one for a recurrent neural network?

Thanks

Hello domokato

Hi guys,

I'm trying to use a genetic algorithm to train a recurrent neural network. I kind of understand what bias nodes are for in feed forward networks. Do I need one for a recurrent neural network?

Thanks

Yes, for the same reason as for feedforward networks. (it permits to shift the activation function along x axis) .

For example, if I have a 2-inputs unit with 1 recurrent loop (on its output), the input vector is for time n : [ input1[sub]n [/sub], input2[sub]n [/sub], output[sub]n-1 [/sub], 1 ]. So 4 weights too.
The output is then computed like in a feedfordward network.

Nico

EDIT :

About bias :

I take this activation function
bool f(float v)
{
return v>0.0f;
}
and I take a unit with 2 boolean inputs with weights equal to 1.

With a bias of 0, the unit performs a OR (input1+input2>0.0)
With a bias of -1, the unit performs a AND (input1+input2-1>0.0)

My point is that a bias must (should) be added to any unit that performs a linear combination of its inputs.

Oh, I get it. Thanks for the explanation

I'm curious, I haven't encountered using a GA to train a neural net before. I guess it's one way to get a large amount of classified training data. How's it working out for you?