python - How to build a neural network with pybrain? -

i new pybrain , having lot of problem in building neural network. documentation not clear me , did not find lot of examples in web.

i neural network 1 input, 1 hidden layer, 1 output.

x--->f1(x),f2(x),...,b---->g(z) 

it should simple example. hidden layer has different function , bias unit. example can consider f1=f2=sigmoid , g custom function.

this have done far not sure @ doing right.

and have no idea of how add bias unit on hidden layer.

class glayer(neuronlayer):      def _forwardimplementation(self, inbuf, outbuf):         outbuf[:]=g(inbuf)       def _backwardimplementation(self, outerr, inerr, outbuf, inbuf):       inerr[:]=derivative(g,inbuf)*outerr   print "build network"  #layer inlayer=linearlayer(1) hlayer=sigmoidlayer(2) outlayer=glayer(1) net=feedforwardnetwork() net.addinputmodule(inlayer) net.addmodule(hlayer) net.addoutputmodule(outlayer) #connection in_to_hidden = fullconnection(inlayer, hlayer) hidden_to_out = fullconnection(hlayer, outlayer) net.addconnection(in_to_hidden) net.addconnection(hidden_to_out) net.sortmodules() 

you add biasunit hidden layer.

hbiaslayer=biasunit()  net.addmodule(hbiaslayer)