Exact repeatability of PyBrain experiments - python-2.7

Question

What parameters in pybrain should be set to ensure exact replication of results when using the neural network modules as shown in the code below?
For each new run, the outputs differ although the random seed is set to the same value. The weights and biases are also the same for each run (due to np.random.seed(0)).
The weights and biases can also be set using net._setParameters(), but the results are also different when following this approach.
#!/usr/bin/python
#Python 2.7
from __future__ import division
import numpy as np
from pybrain.structure import SigmoidLayer, LinearLayer, TanhLayer
from pybrain.datasets import SupervisedDataSet
from pybrain.supervised.trainers import BackpropTrainer
from pybrain.tools.shortcuts import buildNetwork
np.random.seed(0)
net = buildNetwork(1,2,1,hiddenclass=SigmoidLayer,outclass=LinearLayer,bias=True)
N = 10
t = np.arange(0,N,1)/N
x = np.cos(2*np.pi*0.1*t)
y = np.cos(2*np.pi*0.1*t)
ds = SupervisedDataSet(1, 1)
for c in range(N):
ds.addSample(x[c], y[c])
#net._setParameters(np.random.normal(0,1,(len(net.params))))
#net._setParameters(np.array([1.0]*len(net.params)))
trainer = BackpropTrainer(net, ds)
print 'NN parameters after setup:'
print net.params
for c in range(2):
e1 = trainer.train()
print 'Epoch %d Error: %f'%(c,e1)
print 'NN parameters after training:'
print net.params
p=np.zeros(N)
for c in range(N):
p[c] = net.activate([x[c]])
err = np.sum((y-p)**2)/N
print 'Prediction error = %2.4f'%err
The output of the code for two consecutive runs:
Run 1:
NN parameters after setup:
[ 1.76405235 0.40015721 0.97873798 2.2408932 1.86755799 -0.97727788
0.95008842]
Epoch 0 Error: 0.258780
Epoch 1 Error: 0.149163
NN parameters after training:
[ 1.63888191 0.40916677 0.97224621 2.24929727 1.8615028 -1.09298541
0.83265293]
Prediction error = 0.2179
Run 2:
NN parameters after setup:
[ 1.76405235 0.40015721 0.97873798 2.2408932 1.86755799 -0.97727788
0.95008842]
Epoch 0 Error: 0.258757
Epoch 1 Error: 0.148765
NN parameters after training:
[ 1.6384432 0.40916969 0.97225458 2.24931834 1.86149186 -1.09343599
0.83221073]
Prediction error = 0.2167
Clearly, the NN parameters before training are identical for both cases. After training, the NN parameters differ (and hence the predicted results and errors during training).