Training Fails for Non-Default Activation Functions

[Google Code Exporter]

I've modified the example for how to use a feed forward network by passing an 
argument to the newff function.

import neurolab as nl
import numpy as np

# Create train samples
x = np.linspace(-7, 7, 20)
y = np.sin(x) * 0.5

size = len(x)

inp = x.reshape(size,1)
tar = y.reshape(size,1)

# Create network with 2 layers and random initialized
net = nl.net.newff([[-7, 7]],[5, 1], transf=[nl.net.trans.LogSig]*2)

# Train network
error = net.train(inp, tar, epochs=500, show=100, goal=0.02)

Original issue reported on code.google.com by [e-mail] on 8 Jun 2014 at 7:31

[Google Code Exporter]

transf gets list of functions, not a classes:

net = nl.net.newff([[-7, 7]],[5, 1], transf=[nl.net.trans.LogSig()]*2)

Original comment by [e-mail] on 9 Jun 2014 at 4:38

• Changed state: Invalid