Tensors and Dynamic neural networks in Python with strong GPU acceleration

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.…

Code and hyperparameters for the paper "Generative Adversarial Networks"

Warning: This project does not have any current developer. See bellow.

Gaussian processes in TensorFlow

Restricted Boltzmann Machines in Python.

Implementation of some deep learning algorithms.

Modular Restricted Boltzmann Machine (RBM) implementation using Theano

Generative moment matching networks

Robust Principal Component Analysis via ADMM in Python

Python algorithms for regularized regression

Example code for the AMS Solar Energy Prediction Contest (http://www.kaggle.com/c/ams-2014-solar-energy-prediction-contest).

Experiments with machine learning approaches to predicting richness (S), abundance (N), energy use (E) & biomass(B)