A playbook for systematically maximizing the performance of deep learning models.

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

local non-uniformity correction for mutual information estimation

Code for Invariant Rep. Without Adversaries (NIPS 2018)

Temporal correlation explanation.

Automated gene expression analysis using CorEx

Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"

Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling

Official Implementation of ICML 2019 Paper. MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing; and UAI 2019 Paper: N-GCN: Multi-scale Graph Convolution for S…

Functional TensorFlow Implementation of Singular Value Decomposition for paper Fast Graph Learning

Project site for "Your Classifier is Secretly an Energy-Based Model and You Should Treat it Like One"

Reconstruction of the fast neural style transfer (Johnson et al.). Some portions of the paper have been improved by the follow-up work like the instance normalization, etc. Checkout transformer_net…

Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally included reconstruction scripts which allow you to reconstruct only the content or the style of the i…

Code for Implicit Generation and Generalization with Energy Based Models

PyTorch implementation of Algorithm 1 of "On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models"

Autoregressive Energy Machines

Continuous Connectivity project

Echo Noise Channel for Exact Mutual Information Calculation

Code for Invariant Rep. Without Adversaries (NIPS 2018)

Implementation of linear CorEx and temporal CorEx.

Computational Neuroscience in Python

Variational Information Maximization for Feature Selection

local non-uniformity correction for mutual information estimation

Fast, linear version of CorEx for covariance estimation, dimensionality reduction, and subspace clustering with very under-sampled, high-dimensional data

Nonlinear Information Bottleneck

The Linear Information Sieve

A flexible version of CorEx developed for bio-data challenges that handles missing data, continuous/discrete variables, multi-CPU, overlapping structure, and includes visualizations

The information sieve for discrete variables.

Transforms univariate data into normally distributed data