Sohl-Dickstein

Diffusion-Probabilistic-Models

Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics

DrBrainlove

Code for regenerating and manipulating label stickers for Dr. Brainlove art car and science outreach project.

fractal

The boundary of neural network trainability is fractal

guided-evolutionary-strategies

Guided Evolutionary Strategies

Hamiltonian-Annealed-Importance-Sampling

Matlab code implementing Hamiltonian Annealed Importance Sampling for importance weight, partition function, and log likelihood estimation for models with continuous state spaces

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

LAHMC

Look Ahead Hamiltonian Monte Carlo

Minimum-Probability-Flow-Learning

Matlab code implementing Minimum Probability Flow Learning.

NL-Augmenter

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

Sum-of-Functions-Optimizer

Implements SFO minibatch optimizer in Python and MATLAB, and reproduces figures from paper.

Sohl-Dickstein/Diffusion-Probabilistic-Models

Reference implementation for Deep Unsupervised Learning using Nonequilibrium Thermodynamics

Sohl-Dickstein/fractal

The boundary of neural network trainability is fractal

Sohl-Dickstein/Sum-of-Functions-Optimizer

Implements SFO minibatch optimizer in Python and MATLAB, and reproduces figures from paper.

Sohl-Dickstein/Minimum-Probability-Flow-Learning

Matlab code implementing Minimum Probability Flow Learning.

Sohl-Dickstein/LAHMC

Look Ahead Hamiltonian Monte Carlo

Sohl-Dickstein/Hamiltonian-Annealed-Importance-Sampling

Matlab code implementing Hamiltonian Annealed Importance Sampling for importance weight, partition function, and log likelihood estimation for models with continuous state spaces

Sohl-Dickstein/DrBrainlove

Code for regenerating and manipulating label stickers for Dr. Brainlove art car and science outreach project.

Sohl-Dickstein/guided-evolutionary-strategies

Guided Evolutionary Strategies

Sohl-Dickstein/jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Sohl-Dickstein/NL-Augmenter

NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations

Sohl-Dickstein/learned_optimization

Sohl-Dickstein/Adv360-Pro-ZMK

Production repository for the all-new Advantage360 Professional using ZMK engine