HUJI Deep Learning Group

caffe-simnets

The SimNets Architecture's Implementation in Caffe

Diffusion-Probabilistic-Models

Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics

FlowKet

A framework based on Tensorflow for running variational Monte-Carlo simulations of quantum many-body systems.

Generative-ConvACs

Experiments from the article "Tensorial Mixture Models"

inductive-pooling

Experiments from the paper "Inductive Bias of Deep Convolutional Networks through Pooling Geometry"

Long-Term-Memory-of-Deep-RNNs

Source code for https://arxiv.org/abs/1710.09431 - On the Long-Term Memory of Deep Recurrent Networks.

OverlapsAndExpressiveness

Experiments for the paper "On the Expressive Power of Overlapping Architectures of Deep Learning"

simnets-tf

SimNets implementation in TensorFlow

spn-poon-2011

Modification of original implementation, for SPN MNIST missing data experiments

sub_task_decomposition

Official implementation of the experiments in the "Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks" paper.

HUJI-Deep/FlowKet

A framework based on Tensorflow for running variational Monte-Carlo simulations of quantum many-body systems.

HUJI-Deep/Generative-ConvACs

Experiments from the article "Tensorial Mixture Models"

HUJI-Deep/caffe-simnets

The SimNets Architecture's Implementation in Caffe

HUJI-Deep/simnets-tf

SimNets implementation in TensorFlow

HUJI-Deep/inductive-pooling

Experiments from the paper "Inductive Bias of Deep Convolutional Networks through Pooling Geometry"

HUJI-Deep/Long-Term-Memory-of-Deep-RNNs

Source code for https://arxiv.org/abs/1710.09431 - On the Long-Term Memory of Deep Recurrent Networks.

HUJI-Deep/Diffusion-Probabilistic-Models

Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics

HUJI-Deep/OverlapsAndExpressiveness

Experiments for the paper "On the Expressive Power of Overlapping Architectures of Deep Learning"

HUJI-Deep/spn-poon-2011

Modification of original implementation, for SPN MNIST missing data experiments

HUJI-Deep/sub_task_decomposition

Official implementation of the experiments in the "Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks" paper.

HUJI-Deep/GSN

Efficient implementation of Generative Stochastic Networks

HUJI-Deep/MAPS

GPU Optimization and Memory Abstraction Framework

HUJI-Deep/netket

Machine learning algorithms for many-body quantum systems

HUJI-Deep/nice

HUJI-Deep/spn-opt-discrim

Adaptation of SPN parameter learning by Zhao et al. to support classification under missing data setting.

HUJI-Deep/tensorflow-wavenet

A TensorFlow implementation of DeepMind's WaveNet paper