Pinned Repositories
gradient-checkpointing
Make huge neural nets fit in memory
iaf
Code for reproducing key results in the paper "Improving Variational Inference with Inverse Autoregressive Flow"
improved-gan
Code for the paper "Improved Techniques for Training GANs"
pixel-cnn
Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"
weightnorm
Example code for Weight Normalization, from "Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks"
deep_q_rl
Theano-based implementation of Deep Q-learning
HiggsML
My second place solution to the Higgs Boson Machine Learning Challenge
LinRegVB
Code for my paper "Fixed-Form Variational Posterior Approximation through Stochastic Linear Regression"
weight_norm
Lasagne code for weight normalization
TimSalimans's Repositories
TimSalimans/weight_norm
Lasagne code for weight normalization
TimSalimans/HiggsML
My second place solution to the Higgs Boson Machine Learning Challenge
TimSalimans/LinRegVB
Code for my paper "Fixed-Form Variational Posterior Approximation through Stochastic Linear Regression"
TimSalimans/deep_q_rl
Theano-based implementation of Deep Q-learning
TimSalimans/Theano
Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.
TimSalimans/atari-demo
Record demonstrations for atari.
TimSalimans/atari-reset
Learn RL policies for Atari by resetting from a demonstration