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

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

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

Machine learning algorithms for many-body quantum systems

SimNets implementation in TensorFlow

Experiments from the article "Tensorial Mixture Models"

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

Modification of original implementation, for SPN MNIST missing data experiments

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

A TensorFlow implementation of DeepMind's WaveNet paper