Questions tagged [pybrain]

PyBrain is an open source machine-learning library for python. It supports a wide range of optimisation techniques, neural networks, reinforcement learning and more.

PyBrain is a machine learning library that can be used by entry-level students but offers the flexibility and algorithms for state-of-the-art research.

For more information, see the PyBrain homepage

310 questions
4
votes
0 answers

Activation value of pybrain recurrent network is zero

I tested a dummy program to get the activation from the hidden layer of the network. from pybrain.tools.shortcuts import buildNetwork from pybrain.datasets import SupervisedDataSet, SequentialDataSet from pybrain.supervised.trainers import…
dnth
  • 879
  • 2
  • 12
  • 22
4
votes
1 answer

How to predict on new data using Pybrain?

What I want to do is ask Pybrain to predict on new data, for example predict(0,1,0,1,1,0) and it should output what the answer it thinks it would be. The question is, what code do I need to paste to make this happen? Additional info: the…
ben olsen
  • 663
  • 1
  • 14
  • 27
4
votes
1 answer

pybrain what is total error and what does it tell us

so I am very new to python and pybrain but I found a code online and ran my own data on it. When i look at the python shell all I see is Total error: 0.119794950183 Total error: 0.120078064472 Total error: 0.119334171755 Total error:…
ben olsen
  • 663
  • 1
  • 14
  • 27
4
votes
3 answers

PyBrain Training Multiple Output Modules

I would like to train a network with multiple output layers. in->hidden->out 1 ->out 2 Is this possible? If so how do I setup the datasets and trainer to accomplish training.
Firestrand
  • 1,305
  • 10
  • 19
4
votes
1 answer

Unable to build the correct ffnn on pybrain

I have trained a ffnn to fit a unknown function with pybrain. I build the ffnn like this net = buildNetwork(1, 2, 1,hiddenclass=TanhLayer) I said to pybrain to print the params of the net with the command print net.params and pybrain return me the…
emanuele
  • 2,519
  • 8
  • 38
  • 56
4
votes
1 answer

PyBrain Predicting Error

I am trying to predict the sale price of a given set of goods. I am using RecurrentNetwork and BackpropTrainer in pybrain. Here is my code, def nnet(train, target, valid): ds = SupervisedDataSet(52-len(NU)+5, 1) for i in…
thilinarmtb
  • 239
  • 4
  • 11
4
votes
1 answer

pybrain activate() output representation

I build this example using pybrain: from pybrain.tools.shortcuts import buildNetwork from pybrain.datasets import SupervisedDataSet from pybrain.supervised.trainers import BackpropTrainer net = buildNetwork(3, 3, 1) dataSet = SupervisedDataSet(3,…
Viliam
  • 196
  • 1
  • 12
4
votes
1 answer

PyBrain how to interpret the results from net.activate?

I've trained a network on PyBrain for purpose of classification and am ready to fire away with specific input. However, when I do classes = ['apple', 'orange', 'peach', 'banana'] data = ClassificationDataSet(len(input), 1,…
user1330974
  • 2,500
  • 5
  • 32
  • 60
3
votes
1 answer

Retrain a pybrain neural network after adding to the dataset

I have a pybrain NN up and running, and it seems to be working rather well. Ideally, I would like to train the network and obtain a prediction after each data point (the previous weeks figures, in this case) has been added to the dataset. At the…
Kallikantzaros
  • 139
  • 3
  • 10
3
votes
1 answer

Is there any way to write the final weights (after all epochs finished) using pybrain?

I have written a program to train my network using pybrain. I have 104 inputs,and 7 outputs in each line of the train file.I have created one hidden layer with length of 50.The network is written in an .xml file.But I dont know how to write the…
3
votes
1 answer

How to compile my python code in cython with external python libs like pybrain

I need more perfomance running my neural network, so I thinked that building it with cython will be good idea. I am building my code like this: from distutils.core import setup from Cython.Build import cythonize setup( ext_modules =…
3
votes
0 answers

Pybrain: 'SupervisedDataSet' object has no attribute '_convertToOneOfMany'

I am trying to understand the pybrain documentation. There is a demo for classification. from pybrain.datasets import ClassificationDataSet from pybrain.utilities import percentError from pybrain.tools.shortcuts import…
Jon.W
  • 129
  • 12
3
votes
2 answers

Neural network input ordering, does it matter?

I have seen similar questions, but most involve preprocessing. Do the order in which the input are ordered have any importance. For example, say I have three features with three examples each such as: [0, 0, 0, .5, .5, .5, 1, 1, 1] Would it make…
shell
  • 1,867
  • 4
  • 23
  • 39
3
votes
1 answer

How to use function normalize() in PyBrain?

I need to normalize my data before training. In pybrain.rl.environments.task there is a function normalize(). But I did not try, does not work, only errors. Unable to call the function for the training data. from pybrain.tools.shortcuts import…
3
votes
2 answers

PyBrain in Anaconda - ImportError: No module named 'structure'

I'm looking for a way to use numpy, scipy and pybrain in python. If I try to install those I get the error: Microsoft Visual C++ 10.0 is required (Unable to find vcvarsall.bat). I have installed visual studio but it still doesn't work. I have tried…
Lucas
  • 165
  • 1
  • 6