Projects

Created the leading Python library for tensor methods, now with 1,000+ GitHub stars and used by researchers worldwide. TensorLy provides a high-level API for tensor decomposition and tensorized neural networks.

Easy configuration of Python projects with minimal boilerplate. A clean, Pythonic approach to configuration management, particularly adapted for deep learning research.

Learning operators that map between function spaces for solving PDEs and scientific computing problems. A new paradigm for AI in science.

The AFEW-VA databaset is a collection of highly accurate per-frame annotations levels of valence and arousal, along with per-frame annotations of 68 facial landmarks for 600 challenging video clips. These clips are extracted from feature films and were also annotated in terms of discrete emotion categories in the form of the AFEW database (that can be obtained there).

Deep tensorized neural networks in PyTorch. Provides out-of-the-box tensor layers, decomposition methods, and utilities for building efficient deep learning models.

This tool, written in Python as a Flask application backed with a MongoDB, allows any number people to annotate video clips per-frame, for valence and arousal, remotely. In addition it can be easily extended to handle more annotations (e.g. discrete emotions).

Quantum machine learning with tensor methods. Bridging quantum computing and tensor decomposition for scalable quantum algorithms.