How can I make this piece of code even faster?

[Peter Otten]

pablobarhamalzas at gmail.com wrote:

> Ok, I'm working on a predator/prey simulation, which evolve using genetic
> algorithms. At the moment, they use a quite simple feed-forward neural
> network, which can change size over time. Each brain "tick" is performed
> by the following function (inside the Brain class):
> 
>     def tick(self):
>         input_num = self.input_num
>         hidden_num = self.hidden_num
>         output_num = self.output_num
>          
>         hidden = [0]*hidden_num
>         output = [0]*output_num
>         
>         inputs = self.input
>         h_weight = self.h_weight
>         o_weight = self.o_weight
>         
>         e = math.e
>         
>         count = -1
>         for x in range(hidden_num):
>             temp = 0
>             for y in range(input_num):
>                 count += 1
>                 temp += inputs[y] * h_weight[count]
>             hidden[x] = 1/(1+e**(-temp))
>         
>         count = -1
>         for x in range(output_num):
>             temp = 0
>             for y in range(hidden_num):
>                 count += 1
>                 temp += hidden[y] * o_weight[count]
>             output[x] = 1/(1+e**(-temp))
>              
>         self.output = output
> 
> The function is actually quite fast (~0.040 seconds per 200 calls, using
> 10 input, 20 hidden and 3 output neurons), and used to be much slower
> untill I fiddled about with it a bit to make it faster. However, it is
> still somewhat slow for what I need it.
>  
> My question to you is if you an see any obvious (or not so obvious) way of
> making this faster. I've heard about numpy and have been reading about it,
> but I really can't see how it could be implemented here.
> 
> Cheers!

Assuming every list is replaced with a numpy.array,

h_weight.shape == (hidden_num, input_num)
o_weight.shape == (output_num, hidden_num)

and as untested as it gets:

    def tick(self):
        temp = numpy.dot(self.inputs, self.h_weight)
        hidden = 1/(1+numpy.exp(-temp))  
        
        temp = numpy.dot(hidden, self.o_weight)
        self.output = 1/(1+numpy.exp(-temp))  

My prediction: this is probably wrong, but if you can fix the code it will 
be stinkin' fast ;)