Foundation Models for Time Series

Reliable Wrist PPG Monitoring by Mitigating Poor Skin Sensor Contact (Nature Scientific Reports)

Differentiable Patch Selection

Diagrams for visualizing neural network architecture

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

Reference PyTorch implementation and models for DINOv3

Shapley Interactions and Shapley Values for Machine Learning

A list of (post-hoc) XAI for time series

An open-source RAG-based tool for chatting with your documents.

Time series distances: Dynamic Time Warping (fast DTW implementation in C)

ClaSPy: A Python package for time series segmentation.

Unified Model Interpretability Library for Time Series

An application to calculate the carbon emissions from crops in South East Asia. A project built in collaboration with Winrock for Grow Asia.

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

A crash course in six episodes for software developers who want to become machine learning practitioners.

Flickr-Faces-HQ Dataset (FFHQ)

Pretrained TorchVision models on CIFAR10 dataset (with weights)

Pretrained models on CIFAR10/100 in PyTorch

The HSIC Bottleneck: Deep Learning without Back-Propagation

Compare neural networks by their feature similarity

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

State-of-the-art pretrained vision model from Bing Multimedia

A pytorch implementation for paper 'Exploring Simple Siamese Representation Learning'

An Numpy and PyTorch Implementation of CKA-similarity with CUDA support

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

Code for paper "Can contrastive learning avoid shortcut solutions?" NeurIPS 2021.