معرفی
Parag Singla is a Professor in the Department of Computer Science and Engineering with a joint appointment at the School of Artificial Intelligence at Indian Institute of Technology Delhi (IIT Delhi). He is an active member of the Data Analytics and Intelligence Research (DAIR) Group at IIT Delhi.
His educational background includes a Ph.D. from the University of Washington, Seattle (2009), where he worked under Pedro Domingos, followed by postdoctoral research with Raymond Mooney at the University of Texas at Austin.
Professor Singla's research focuses on bridging neural networks with symbolic reasoning to create more robust AI systems that can incorporate domain knowledge and constraints. His work aims to develop models that function effectively even with limited data, moving toward more general human-like intelligence. His earlier contributions to Statistical Relational Learning (SRL) include significant work on Markov Logic and the development of Alchemy, the first open-source implementation of Markov Logic.
Among his notable technical contributions is the invention of Lifted First-order Belief Propagation, a foundational algorithm for efficient inference in Statistical Relational Learning models that exploits model symmetry to scale inference and learning processes.
His research has applications in natural language processing and computer vision, with emphasis on solving problems that were previously intractable with purely neural or purely symbolic approaches.
