David Krueger's repositories
Blocks_quickstart
This repo contains a simple demo of Blocks and Fuel, explaining their basic functionality.
Active-Learning-Bayesian-Convolutional-Neural-Networks
Active Learning on Image Data using Bayesian ConvNets
actor-critic-public
The source code for "An Actor Critic Algorithm for Structured Prediction"
async-rl
Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"
async_deep_reinforce
Asynchronous Methods for Deep Reinforcement Learning
attention-lvcsr
End-to-End Attention-Based Large Vocabulary Speech Recognition
blocks
A Theano framework for building and training neural networks
blocks-examples
Examples and scripts using Blocks
blocks-extras
A collection of extensions to the Blocks framework
CS188.1x-Project3
This was the third project for Berkeley's CS188.1x. Topics included MDP with Value Iteration and Policy iteration. These topics were practiced with Pacman, a robot learning to move across the screen, and a game called GridWorld
fuel
A data pipeline framework for machine learning
handwriting
Conditional handwriting generation in Theano
Lasagne
Lightweight library to build and train neural networks in Theano
NeuroBricks
A theano warpper for implementing, training and analysing neural nets with convenience.
nips2015-action-conditional-video-prediction
Implementation of "Action-Conditional Video Prediction using Deep Networks in Atari Games"
nolearn
Abstractions around neural net libraries, most notably Lasagne.
ntm-lasagne
Neural Turing Machines library in Theano with Lasagne
platoon
Multi-GPU mini-framework for Theano
raccoon
Monitoring library for Theano
Recipes
Lasagne recipes: examples, IPython notebooks, ...
seq2seq_experiments
Learning to execute Python in Tensorflow and other Seq2seq examples
smartdispatch
An easy to use job launcher for supercomputers with PBS compatible job manager.
tensorflow
Open source software library for numerical computation using data flow graphs.
Theano-Tutorials
Bare bones introduction to machine learning from linear regression to convolutional neural networks using Theano.
zoneout
Code for experiments with our RNN regularizer, which stochastically forces units to maintain previous values.