30 open source projects by karpathy

VQVAEs, GumbelSoftmaxes and friends

An Academic Papers Management and Discovery System

A Random Forest implementation for MATLAB. Supports arbitrary weak learners that you can define.

Scripts that generate .html to more easily see NIPS papers

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Automating research publications discovery and analysis. For example, ever wish your computer could automatically open papers that are most similar to a paper at an arbitrary url? How about finding all papers that report results on some dataset? Let's re-imagine literature review.

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.

tensorflow reinforcement learning agents for OpenAI gym environments

Reinforcement Learning Agents in Javascript (Dynamic Programming, Temporal Difference, Deep Q-Learning, Stochastic/Deterministic Policy Gradients)

Deep Recurrent Neural Networks and LSTMs in Javascript. More generally also arbitrary expression graphs with automatic differentiation.

Automatically collect and visualize usage statistics in Ubuntu/OSX environments.

Implementation of t-SNE visualization algorithm in Javascript.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Normalizing flows in PyTorch. Current intended use is education not production.

Support Vector Machine in Javascript (SMO algorithm, supports arbitrary kernels) + GUI demo

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

Efficient Image Captioning code in Torch, runs on GPU

Web interface for browsing, search and filtering recent arxiv submissions

MADE (Masked Autoencoder Density Estimation) implementation in PyTorch

my blog

Aspires to help the influx of bioRxiv / medRxiv papers on COVID-19

Notebooks and various random fun

Find people you should follow on Twitter based on who the people you follow follow

Random Forest implementation for JavaScript. Supports arbitrary weak learners. Includes interactive demo.

Random notes on papers, likely a short-term repo.

Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes

A wrapper for LibSVM that lets you train SVM's directly on Eigen library matrices in C++

Game making library for using Canvas element

arxiv-sanity lite: tag arxiv papers of interest get recommendations of similar papers in a nice UI using SVMs over tfidf feature vectors based on paper abstracts.