Talks & Seminars
Title: Markov Logic: Theory, Algorithms and Applications
Parag Singla, University of Washington, Seattle
Date & Time: April 17, 2008 12:00
Venue: K.R. Conference room, ā€˜Cā€™ Block, 1st floor, Kanwal Rekhi Building
AI systems must be able to reason about complex objects as well explicitly handle uncertainty. First order logic gives the formalism to handle the first. Probability gives the power to handle the latter. Combining the two has been a long standing goal of AI research. In this talk, I will present Markov Logic (Richardson & Domingos 06), which combines the power of full first order logic and Markov networks. Markov logic represents the underlying world by attaching real valued weights to formulas in first order logic. The formulas in Markov logic can be seen as defining templates for ground Markov networks. Carrying out prepositional inference techniques in such models leads to explosion in time and memory. I will present two algorithms: LazySAT (lazy WalkSAT) and lifted belief propagation, to Overcome these problems. Learning of the parameters (formula weights) is done using a voted perceptron algorithm. I will then present applications to the problems of entity resolution and identification of social relationships in consumer photo collections. I will conclude the talk with directions for future work.
Speaker Profile:

He did his bachelors in Computer Science & Engineering from IIT Bombay in 2002. He then joined University of Washington for graduate studies in Computer Science. He finished his Masters in 2004 and is on his way to complete his PhD in August 2008. His PhD advisor is Pedro Domingos. He has several publications in premiere AI, data mining and IR conferences such as AAAI, UAI, ICDM, PKDD and WWW. He has been a reviewer for the journals TKDD and AMAI. He has also filed two patents. He has interned at top research institutions including IBM IRL and Microsoft research Redmond.

His research areas include machine learning, data mining and social networks analysis. Specifically, his PhD research has been around the development of Markov logic, one of the most powerful models for statistical relational AI. He is also a co-author for Alchemy, an open source software for statistical relational AI developed at the University of Washington.

Full Vita at: http://www.cs.washington.edu/homes/parag/parag-resume.pdf
List of Talks


Faculty CSE IT
Forgot Password
    [+] Sitemap     Feedback