About

Hari Prasanna Das is a final year Ph.D. candidate in the Department of Electrical Engineering and Computer Sciences at UC Berkeley. His current research interests include Deep Learning, Computer Vision, Transfer Learning, Occupant Modeling, and Smart and Energy-Efficient Buildings. He is advised by Prof. Costas J. Spanos and has developed a deep learning-based generative framework to extract conditional feature representation and generate conditional synthetic data to tackle data insufficiency challenges. Hari has improved the generalizability of personal thermal comfort prediction algorithms by 16% via transfer learning. He has also developed deep learning algorithms for occupant activity detection in smart buildings using privacy-preserving WiFi signals. The system achieved a 97.5% accuracy in occupant activity detection. Additionally, he has designed a graphical lasso-based framework to intelligently segment the players in energy game-theoretic frameworks into energy usage groups, crucial in smart incentive design. Hari has worked as a Software Engineer and Research Scientist at Amazon and ByteDance, respectively. As part of Amazon Alexa AI, he worked on the NLP engine of Alexa to enhance its contextual question-answer capability. He implemented Contextual Bandits and Prioritized Experience Replay to improve follow-up question-answer performance by 17%. He also introduced and implemented an Online Learning pipeline for continual training and adaptation of the model. At ByteDance, Hari conducted an extensive survey on a new area of research- Foundation Models (FM) and its implementation. He proposed a research approach to using FMs in a distributed learning setting, combining training, aggregation, and online temporal updating of FMs. He designed a proof-of-concept implementation of the above approach to introduce high performance and communication-efficient federated multi-task learning for ByteDance products. Hari holds a Ph.D. in Electrical Engineering and Computer Sciences from the University of California, Berkeley, and a Bachelor of Technology (BTech) in Electrical Engineering from IIT. He is proficient in ML, Deep Learning, Computer Vision, AI, and NLP. He is currently looking for full-time roles in Applied Machine Learning Research and Development.