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
0
votes
1 answer

PyBrain mnist classification

I'm trying to classificate mnist data with PyBrain. Below is code for training: def train_net(self): print("Build network") net = buildNetwork(784, 30, 10, bias=True, hiddenclass=TanhLayer, outclass=SoftmaxLayer) back_trainer =…
Long Smith
  • 1,339
  • 3
  • 21
  • 40
0
votes
1 answer

Python Module Update

I have a main file that imports a class from another file as such: from pybrain.rl.environments.HoldemTask import HoldemTask. When I change HoldemTask.py, the changes are not reflected in the main file. The only workaround I have found is to run…
Eric Gorlin
  • 319
  • 1
  • 8
0
votes
1 answer

What's the Total error mean in pybrain during training?

Here is my code: from pybrain.structure import * from pybrain.datasets import SupervisedDataSet from pybrain.supervised.trainers import BackpropTrainer fnn = FeedForwardNetwork() inLayer = LinearLayer(2, name='inLayer') hiddenLayer = SigmoidLayer(7,…
程书意
  • 1
  • 1
  • 5
0
votes
2 answers

Q Learning coefficients overflow

I've been using the blackbox challenge (www.blackboxchallenge.com) to try and learn some reinforcement learning. I've created a task and an environment for the challenge and I'm using PyBrain to train based on the black box environment. The summary…
0
votes
1 answer

pybrain NNregression tool parameters

I'm trying to use the NNregression tool in pybrain: http://pybrain.org/docs/api/tools.html I have my dataset: ds = SupervisedDataSet(20,1) for x, y in zip(inputs, outputs): ds.appendLinked(x,y) And I can get the network to train with the…
user5859747
0
votes
1 answer

Regression with PyBrain

I'm trying to build a surrogate model for 100 samples. I have two inputs and two responses all of which are normalised with the magnitude of their respective maxima. Normalisation: for i in range(0, len(array(self.samples)[0])): …
newkid
  • 1,368
  • 1
  • 11
  • 27
0
votes
2 answers

PyBrain: overflow encountered in square, invalid value encountered in multiply

I create a neural network like this: n = FeedForwardNetwork() inLayer = LinearLayer(43) bias = BiasUnit() hiddenLayer = SigmoidLayer(100) outLayer =…
Luke
  • 1,369
  • 1
  • 13
  • 37
0
votes
0 answers

Genetic Algorithm and neural network failing to learn

I am trying to make a Flappy Bird AI where the agent tries to learn to pass through the pipes via genetic algorithms and neural network. My implementation is that I am using a neural network with two inputs (horizontal distance from pipe and…
0
votes
1 answer

Pybrain implement network whose outputs are parameters of a function

I want to build a neural network in pybrain to fit the following function z(t) = A + B x(t) + C(t) y(t) Here, (x, y, z)(t) are my experimental data; A and B are constants and C(t) is a function of time. The requirements for my network are: Input…
0
votes
0 answers

I have Installed pybrain on python on ubuntu 12.04 but showing errors

I have install pybrain module inside python 2.7 I have installed pybrain but showing this error import pybrain Traceback (most recent call last): File "bpa_pybrain1.py", line 1, in import pybrain File…
0
votes
1 answer

In PyBrain, when creating artificial neural networks, are the inputs to a neuron weighted and summed before being passed into the activation function?

I'm taking an introduction to machine learning class in school and all the ANN we've been shown have the inputs weighted and summed before being inputted into the activation function of any neuron. I'm creating an ANN for homework and I was…
itsSLO
  • 359
  • 1
  • 4
  • 10
0
votes
1 answer

PyBrain LSTM Example resultin in ValueError:Attempted relative import in non-package

I'm trying to run an LSTM network for like two weeks now and I cant find a good framework to do so. I'm actually trying with PyBrain which has this directory hierarchy: pybrain/ ... examples/ ... supervised/ ... …
Lucas Azevedo
  • 1,867
  • 22
  • 39
0
votes
1 answer

PyBrain Neural Network force initialisation

I have a neural network running in pybrain and I'm happy enough with the correctness of it, now I just want to improve the accuracy. Until I begin experimenting with the various parameters, however, I want to be sure I am starting this exploration…
Philip O'Brien
  • 4,146
  • 10
  • 46
  • 96
0
votes
1 answer

Classification points based on their position

I would like to train, ask and check my Neural Network with points positions. I have got a file with INI file structure which contain a list of points sorted by their class. For example: [points] c_0 = (0, 0)#(1, 1)#(0,1) c_1 = (5, 5)#(6, 6)#(10,…
Marek
  • 1,189
  • 3
  • 13
  • 33
0
votes
1 answer

PyBrain: MemoryError: while loading training dataset

I am trying to train a feedforward neural network, for binary classification. My Dataset is 6.2M with 1.5M dimension. I am using PyBrain. I am unable to load even a single datapoint. I am getting MemoryError. My Code snippet is: Train_ds =…
Anuj Gupta
  • 6,328
  • 7
  • 36
  • 55