Deep neural network implementation without the learning cliff! This library implements multi-layer perceptrons as a wrapper for the powerful pylearn2 library that's compatible with scikit-learn for a more user-friendly and Pythonic interface.

NOTE: This project is possible thanks to the nucl.ai Conference on July 20-22. Join us in Vienna!

Thanks to the underlying pylearn2 implementation, this library supports the following neural network features, which are exposed in an intuitive and well documented API:

• Activation Types —

  • Nonlinear: Sigmoid, Tanh, Rectifier, Maxout.
  • Linear: Linear, Gaussian, Softmax.

• Layer Types — Convolution (greyscale and color, 2D), Dense (standard, 1D).
• Learning Rules — sgd, momentum, nesterov, adadelta, adagrad, rmsprop.
• Regularization — L1, L2 and dropout.
• Dataset Types — numpy.ndarray, scipy.sparse, coming soon: iterators.

If a feature you need is missing, consider opening a GitHub Issue with a detailed explanation about the use case and we'll see what we can do.

If you want to use the latest official release, you can get it from PYPI directly:

> pip install scikit-neuralnetwork

This contains its own packaged version of pylearn2 from the date of the release (and tag) but will use any globally installed version if available.

You'll need to first install some dependencies manually. Unfortunately, pylearn2 isn't yet installable via PyPI and recommends an editable (pip -e) installation:

> pip install numpy scipy theano
> pip install -e git+https://github.com/lisa-lab/pylearn2.git#egg=Package

Once that's done, you can grab this repository and install from setup.py in the exact same way:

> git clone https://github.com/aigamedev/scikit-neuralnetwork.git
> cd scikit-neuralnetwork; python setup.py develop

This will make the sknn package globally available within Python as a reference to the current directory.

Then, you can run the samples and benchmarks available in the examples/ folder, or launch the tests to check everything is working:

> pip install nose
> nosetests -v sknn.tests

We strive to maintain 100% test coverage for all code-paths, to ensure that rapid changes in the underlying pylearn2 library are caught automatically.

To run a visualization that uses the sknn.mlp.Classifier just run the following command in the project's root folder:

> python examples/plot_mlp.py --params activation

There are multiple parameters you can plot as well, for example iterations, rules or units. The datasets are randomized each time, but the output should be an image that looks like this...

The following section compares nolearn (and lasagne) vs. sknn (and pylearn2) by evaluating them as a black box. In theory, these neural network models are all the same, but in practice every implementation detail can impact the result. Here we attempt to measure the differences in the underlying libraries.

The results shown are from training for 10 epochs for two-thirds of the original MNIST data, on two different machines:

1. GPU Results: NVIDIA GeForce GTX 650 (Memory: 1024Mb, Cores: 384) on Ubuntu 14.04.
2. CPU Results: Intel Core i7 2Ghz (256kb L2, 6MB L3) on OSX Mavericks 10.9.5.

You can run the following command to reproduce the benchmarks on your machine:

> python examples/bench_mnist.py (sknn|lasagne)

... to generate the statistics below (e.g. over 25 runs).

All the neural networks were setup as similarly as possible, given parameters that can be controlled within the implementation and their interfaces. In particular, this model has a single hidden layer with 300 hidden units of type Rectified Linear (ReLU) and trained with the same data with validation and monitoring disabled. The remaining third of the MNIST dataset was only used to test the score once training terminated.

WARNING: These numbers should not be considered definitive and fluctuate as the underlying libraries change. If you have any ideas how to make the accuracy results similar, then please submit a Pull Request on the benchmark script.

The library supports both regressors (to estimate continuous outputs from inputs) and classifiers (to predict labels from features). This is the sklearn-compatible API:

from sknn.mlp import Classifier, Layer

nn = Classifier(
    layers=[
        Layer("Rectifier", units=100),
        Layer("Linear")],
    learning_rate=0.02,
    n_iter=10)
nn.fit(X_train, y_train)

y_valid = nn.predict(X_valid)

score = nn.score(X_test, y_test)

The generated documentation as a standalone page where you can find more information about parameters, as well as examples in the User Guide.

• PyLearn2 by LISA Lab — The amazing neural network library that powers sknn.
• Theano by LISA Lab — Underlying array/math library for efficient computation.
• scikit-learn by INRIA — Machine learning library with an elegant Pythonic interface.
• nolearn by dnouri — Similar wrapper library for Lasagne compatible with scikit-learn.
• Lasagne by benanne — Alternative deep learning implementation using Theano too.