TCG CREST

Avisek Gupta works in machine learning and deep learning, with a focus on unsupervised and weakly supervised learning. He is particularly interested in how low-effort supervision from experts can be provided to guide the learning procedure of a statistical model. Recent projects that he has worked on include (i) classification of Alzheimer’s disease and medical report generation, (ii) unsupervised identification of distinct speakers from spoken audio, and (iii) applying machine learning to combinatorial problems, such as forming coalitions in multi-agent systems.

 

Avisek Gupta received his Ph.D. in Computer Science at the Indian Statistical Institute, Kolkata in 2021. Prior to joining IAI, he worked as a Visiting Scientist at the Electronics and Communication Sciences Unit (ECSU), Indian Statistical Institute, Kolkata. He received his M.E. degree from Jadavpur University in Computer Science & Engineering in 2014, and his B.Tech. in Computer Science & Engineering from the West Bengal University of Technology (currently the Maulana Abul Kalam Azad University of Technology, West Bengal) in 2012.

 

At IAI, Avisek Gupta has taught courses on Deep Learning (2025,2024,2023), Machine Learning (2022), and Probability and Statistics (2023). He is on the external advisory committee, and serves as an instructor for the annual Winter School on Deep Learning WSDL-2025/2024/2023/2022, organized by the Electronics and Communication Sciences Unit, at the Indian Statistical Institute, Kolkata.

 

For more information you can visit: https://avisekgupta.github.io/