[month] [year]

Prof. Ambuj K Singh

Prof. Ambuj K Singh, University of California, Santa Barbara (UCSB) gave a talk on Representations in deep learning and the brain on 3 December at KRB Auditorium. 

Artificial intelligence and machine learning have been extremely successful in predicting, optimizing, and controlling the behaviour of complex interacting systems. Robustness and explainability of existing methods, however, remains a challenge. I will introduce some ideas on how to analyse the space of representations produced by deep learning, how representation patterns are intricately connected to the machine learning tasks, and how they also drive the robustness and explainability of models. In the second part of the talk, I will focus on complex multimodal representations produced by the brain, how they can reveal brain organizational structures, and how they can be used to generate complex high-fidelity imagery from brain signals. At the end, we will return to the theme of brain and AI duality in the context of graph representations.

Ambuj K Singh is a Distinguished Professor of Computer Science at the University of California, Santa Barbara, with a part-time appointment in the Biomolecular Science and Engineering Program. He received a B.Tech. degree from the Indian Institute of Technology, Kharagpur, and a PhD degree from the University of Texas at Austin. His research interests are broadly in the areas of machine learning, network science, and chemistry/biology. He has published about 300 technical papers over his career. He has led several multidisciplinary projects including UCSB’s Information Network Academic Research Center funded by the Army, Interdisciplinary Graduate Education Research and Training (IGERT) program on Network Science funded by the NSF, and the Multidisciplinary University Research Initiative (MURI) on Network Science of Teams funded by the US Army. His research has also been funded by the National Institute of Health and the Defense Threat Reduction Agency. He has graduated over 50 graduate students over his career, including over 30 PhD students

December 2024