neupy 0.3.1

NeuPy is the Artificial Neural Network library implemented in Python.

NeuPy v0.3.1 (beta)

NeuPy is a Python library for Artificial Neural Networks.

Installation

$ pip install neupy

Links

• Quick start

• Documentation

• Articles

• Cheat sheet

• Open Issues

Articles

• Password recovery

• Discrete Hopfield Network

• Boston house-prices dataset

• Visualize Backpropagation Algorithms

• MNIST classification

Examples

MLP Neural Networks

• MNIST, Multilayer perceptron

• Rectangle images, Multilayer perceptron

• Boston House Price prediction, Hessian algorithm

• Learning Algorithms Visualization, Gradient Descent, Momentum, RPROP and Conjugate Gradient

• IMDB review classification using CBOW and RPROP MLP

Convolutional Neural Networks

• MNIST CNN

• CIFAR10 CNN

Autoencoders

• MNIST, Denoising Autoencoder

• MNIST, Convolutional Autoencoder

• MNIST, Stacked Convolutional Autoencoders

Competitive Neural Networks

• Simple SOFM example

Neural Networks with Radial Basis Functions

• Classify iris dataset, Probabilistic Neural Network (PNN)

• Regression using Diabetes dataset, Generilized Neural Nerwork (GRNN)

• Music-Speech audio classification, Probabilistic Neural Network (PNN)

Memory based Neural Networks

• Sinus function approximation, CMAC

• Visualize Discrete Hopfield Neural Network energy function

• Password recovery, Discrete Hopfield Neural Network

Boltzmann Machine

• Feature Learning from the MNIST Images, Restricted Boltzmann Machine (RBM)

• Gibbs sampling using face images, Restricted Boltzmann Machine (RBM)

Dependencies

• Python 2.7, 3.4, 3.5

• Theano >= 0.8.1

• NumPy >= 1.9.0

• SciPy >= 0.14.0

• Matplotlib >= 1.4.0

Next steps

• Adding reccurent neural network layers (Issue #57)

• Bug fixing and version stabilization (Known bugs)

• Speeding up algorithms

• Adding more algorithms