nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) trainingchar-rnn
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torchconvnetjs
Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.nn-zero-to-hero
Neural Networks: Zero to Heromicrograd
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like APIneuraltalk2
Efficient Image Captioning code in Torch, runs on GPUneuraltalk
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.arxiv-sanity-preserver
Web interface for browsing, search and filtering recent arxiv submissionsng-video-lecture
reinforcejs
Reinforcement Learning Agents in Javascript (Dynamic Programming, Temporal Difference, Deep Q-Learning, Stochastic/Deterministic Policy Gradients)makemore
An autoregressive character-level language model for making more thingscryptos
Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposesrandomfun
Notebooks and various random funulogme
Automatically collect and visualize usage statistics in Ubuntu/OSX environments.recurrentjs
Deep Recurrent Neural Networks and LSTMs in Javascript. More generally also arbitrary expression graphs with automatic differentiation.arxiv-sanity-lite
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.tsnejs
Implementation of t-SNE visualization algorithm in Javascript.pytorch-normalizing-flows
Normalizing flows in PyTorch. Current intended use is education not production.paper-notes
Random notes on papers, likely a short-term repo.svmjs
Support Vector Machine in Javascript (SMO algorithm, supports arbitrary kernels) + GUI demopytorch-made
MADE (Masked Autoencoder Density Estimation) implementation in PyTorchkarpathy.github.io
my bloglecun1989-repro
Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world application of a neural net trained with backpropagation.deep-vector-quantization
VQVAEs, GumbelSoftmaxes and friendscovid-sanity
Aspires to help the influx of bioRxiv / medRxiv papers on COVID-19find-birds
Find people you should follow on Twitter based on who the people you follow followforestjs
Random Forest implementation for JavaScript. Supports arbitrary weak learners. Includes interactive demo.researchlei
An Academic Papers Management and Discovery SystemRandom-Forest-Matlab
A Random Forest implementation for MATLAB. Supports arbitrary weak learners that you can define.researchpooler
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.nipspreview
Scripts that generate .html to more easily see NIPS papersttmik
Talk to me in Korean Anki cards and related scriptstf-agent
tensorflow reinforcement learning agents for OpenAI gym environmentsgitstats
A lightweight/pretty visualizer for recent work on a git code base in multiple branches. Helps stay up to date with teams working on one git repo in many branches.EigenLibSVM
A wrapper for LibSVM that lets you train SVM's directly on Eigen library matrices in C++MatlabWrapper
C++ convenience class to communicate with a Matlab instance. Send matrices back and forth, execute arbitrary Matlab commands, or drop into interactive Matlab session right in the middle of your C++ code.twoolpy
useful scripts to work with Twitter + Python. Requires the tweepy library.notpygamejs
Game making library for using Canvas elementscholaroctopus
A set of tools/pages that help explore academic literaturekarpathy
root repoLove Open Source and this site? Check out how you can help us