My research interests are deep representation learning, multimodal learning, and generative models with applications to image, audio, video modalities, and medical imaging. Some of my research publication are:
I also worked on Reinforcement Learning [NeurIPS Deep RL Workshop 2015] and Computer Vision problems (traffic sign recognition; age and gender recognition from human faces).
My slides on “Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling” from the reading group can be found by this link