Clone this wiki locally
This list is far from complete. Please feel free to add to this list!
Tutorials and sample code
- Deep Learning Tutorials: A great intro to Theano. There's a companion website.
- Using convolutional neural nets to detect facial keypoints tutorial
- Bare bones introduction to machine learning
Libraries built on Theano
- Downhill: Provides algorithms for minimizing scalar loss for Theano functions.
- sklearn-theano: A sklearn interface for preprocessing using learnt models that use Theano.
- Theano_lgpl: Theano extension that use lgpl code. See that page for a list what is add.
- Mariana: A machine learning framework that aims at greatly simplifying the writing and handling of neural networks (Especially deep ones).
- Passage: A little library for text analysis with RNNs.
- PyAutoDiff: Automatic differentiation for NumPy code.
- GroundHog: An RNN framework.
- theano-rnn theano-rnn: Recurrent neural network implementation. (2 differents implementations)
- Morb: a modular RBM implementation in Theano
- PyMC 3.0: Bayesian statistical modeling and model fitting which focuses on advanced Markov chain Monte Carlo fitting algorithms.
- MonteTheano: Sampling for directed graphical models, more probability distributions than in Theano itself.
- Ape(status alpha): Theano/MPI bridge which will also try to statically schedule the operation onto heterogeneous hardware.
- Crino: a neural-network library based on Theano
- Theanet: Theano based Convolutional Neural Network for image classification with Elastic Distortion & Noising of inputs, Dropout, Maxnorm Regularization, Softmax, Mixture of Gaussians outputs etc.
- Lasagne: a lightweight library to build and train neural networks in Theano, with a focus on feed-forward neural networks but there are extensions for RNNs including LSTMs.
- Blocks: a framework that helps you build neural network models on top of Theano. Includes RNNs.
- Keras: a minimalist, highly modular neural network library in the spirit of Torch.
- Kaldi+PDNN Kaldi+PDNN builds state-of-the-art DNN acoustic models using the open-source Kaldi and PDNN toolkits
- Plato: A simplified API and deep learning library built on top of Theano. Includes MLPs, RBMs, Deep Belief Nets, LSTMs, Variational Autoencoders, Difference Target Prop, etc. Tutorial
- OpenDeep a Torch-like modular framework built on Theano with included models for CNNs, RBMs, RNNs, GSNs, LSTMs and more coming. Current status of the software is alpha.
- nnet-ts Neural network architecture for time series forecasting.
- pyfolio A Python library for performance and risk analysis of financial portfolios (use PyMC3 that use Theano)
- tmetrics A collections of metrics and loss functions written in Theano
- pymanopt Manifold optimization using Theano for gradient (and Hessian) calculations, and code ported from manopt for the optimization.
- ELEKTRONN A highly configurable toolkit with focus on high throughput analysis of large scale 2d and 3d images with convolutional neural networks e.g. in connectomics applications.
Models (not all models, only a few. Frameworks based on Theano have more)
- NADE/RNADE Check the paper/code for RNADE
- Alex's conv net Alex Krizhevsky Conv net in Theano.
- RNN CTC
- Generate natural language descriptions for YouTube videos
- Variational Recurrent Neural Networks
- Transfer Learning
- Neural network that can generate natural images
- 2D Pose Estimation (ICLR 2014): Learning Human Pose Estimation Features with Convolutional Networks (http://arxiv.org/abs/1312.7302). Includes code to download and process data, train and test the model.
- Galaxy morphology prediction: winning solution for the Galaxy Zoo Challenge on Kaggle.
Toolkits / ops
- Artificial Dataset Generation: this dataset generation can be used to do emperical measurements of Machine Learning algorithms.
- Hessian Free: Code to implement Hessian-Free model
- Janus: Janus is a tool that allows NumPy and Theano to be used simultaneously with no additional code.
- Kaldi wrapper They require boost::python
Some specific function requested on the mailing list
Nesterov's accelerated gradient
- Adam's optimizer Code to reproduce "Semi-Supervised Learning with Deep Generative Models" NIPS 2014 paper.
- Pylearn2: A machine learning library.
- DeepANN: Deep ANN implementation.
- TheanoConv3d2d: (Now integrated in Theano) A GPU-friendly 3D convolution implementation based on Conv2D.
Didn't find what you were looking for? Try a github search: