In this solo project we develop a two-stream DL architecture that can accurately recognize and classify different styles of martial arts.
For the training of this ML system we construct a completely new dataset, from publicly available video data.
Tags: Computer Vision, Video Learning, (Skeleton Based) Human Action Recognition
Research work on the application of neural networks and other machine learning techniques in the classification of solutions to the Einstein equations.
Collaboration with Prof. Yang-Hui He at University of Oxford.
Tags: Neural networks, multi-class classification algorithms, PCA and dimensionality reduction.
Currently working on an extension of the above mentioned Martial Arts Project, using state of the art Reinforcement Learning techniques.