kaishengtai
Follow
Stars
Spartan is an algorithm for training sparse neural network models. This repository accompanies the paper "Spartan Differentiable Sparsity via Regularized Transportation" (NeurIPS 2022).
Sinkhorn Label Allocation is a label assignment method for semi-supervised self-training algorithms. The SLA algorithm is described in full in this ICML 2021 paper: https://arxiv.org/abs/2102.08622.
Algorithms, 4th edition textbook code and libraries
End-to-end earthquake detection pipeline via efficient time series similarity search
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
PyTorch implementation of efficient algorithms for DRO with CVaR and Chi-Square uncertainty sets
Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.
Puffer is a free live TV streaming website and a research study at Stanford using machine learning to improve video streaming
Open source neural network chess engine with GPU acceleration and broad hardware support.
Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
PyTorch implementation of image classification models for CIFAR-10/CIFAR-100/MNIST/FashionMNIST/Kuzushiji-MNIST/ImageNet
Sketching linear classifiers over data streams with the Weight-Median Sketch (SIGMOD 2018).
Equivariant Transformer (ET) layers are image-to-image mappings that incorporate prior knowledge on invariances with respect to continuous transformations groups (ICML 2019). Paper: https://arxiv.…
Benchmarks of approximate nearest neighbor libraries in Python
Tensors and Dynamic neural networks in Python with strong GPU acceleration
DAWNBench: An End-to-End Deep Learning Benchmark and Competition
A Python-embedded modeling language for convex optimization problems.
C++ tensors with broadcasting and lazy computing
MacroBase: A Search Engine for Fast Data
ASAP: Prioritizing Attention via Time Series Smoothing
LIBLINEAR -- A Library for Large Linear Classification
Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.
Four Experiments in Handwriting with a Neural Network
Your favorite language gets closer to bare metal.