Academic Projects

Deep Learning

Unitary/Orthogonal matrices are known best solving gradient vanishing/explosion problems. This approach leads to new type of RNNs and has the potential to next level natural language models. It can also be applied to meta learning and reinforcement learning models.

Rotational Unit of Memory

Rumen Dangovski*, Li Jing*, Marin Soljačić

Transactions of the Association for Computational Linguistics

PDF Poster Webpage Code-Tensorflow

Gated Orthogonal Recurrent Units: On Learning to Forget

Li Jing*, Çağlar Gülçehre*, John Peurifoy, Yichen Shen, Max Tegmark, Marin Soljačić, Yoshua Bengio

Neural Computation

PDF Poster Webpage Code-Tensorflow

Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs

Li Jing*, Yichen Shen*, Tena Dubček, John Peurifoy, Scott Skirlo, Yann LeCun, Max Tegmark, Marin Soljačić

International Conference on Machine Learning (ICML) 2017

PDF Poster Slides Webpage Code-Tensorflow Code-Theano

AI for Physics

Applying modern deep learning tools to frontier physics research with massive data has significant advantage. Unconscious reasoning plays an important role in human decision. This is the same for physical world. Going with data directly and building intuitive models surprisingly provide rich understanding in physics.

Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks

John Peurifoy, Yichen Shen, Li Jing, Yi Yang, Fidel Cano-Renteria, Brendan Delacy, John D. Joannopoulos, Max Tegmark, Marin Soljačić

Science Advance

PDF Poster Code News Coverage