A minimal, responsive, and feature-rich Jekyll theme for technical writing.

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

News, full-text, and article metadata extraction in Python 3. Advanced docs:

Lots of metrics for quantifying gerrymandering. 🇺🇸

Python code for part 2 of the book Causal Inference, by Miguel Hernán and James Robins

Collaborative lecture notes for Spring '19 NYU DL class

Precinct shapes (and vote results) for US elections past, present, and future

Open source release of the evaluation benchmark suite described in "Realistic Evaluation of Deep Semi-Supervised Learning Algorithms"

Mathematics of Deep Learning, Courant Insititute, Spring 19

OBS Studio - Free and open source software for live streaming and screen recording

A Theme for GitHub Pages

Pretrained models for TensorFlow.js

temporal action detection with SSN

Code for "The Reversible Residual Network: Backpropagation Without Storing Activations"

WebGL-accelerated ML // linear algebra // automatic differentiation for JavaScript.

A WebGL accelerated, browser based JavaScript library for training and deploying ML models.

🎨 Buttery Smooth Automatic Differentiation in C++

Opinionated stacks of ready-to-run Jupyter applications in Docker.

A TensorFlow implementation of Baidu's DeepSpeech architecture

PArallel Distributed Deep LEarning

Fabrik – Collaboratively build, visualize, and design neural nets in the browser

Model configurations

Computation using data flow graphs for scalable machine learning

Use PaddlePaddle models with one line of code and no setup

Tensorflow wrapper for DataFrames on Apache Spark