[talks] Colloquium Speaker- Percy Liang Thurs Oct 1, 12:30pm

Nicole E. Wagenblast nwagenbl at CS.Princeton.EDU
Mon Sep 28 14:52:36 EDT 2015

Correction- this talk will be at 12:30pm. 

Nicole Wagenblast 
Computer Science Department 
Princeton University 
35 Olden Street 
Princeton, NJ 08540 

----- Original Message -----

From: "Nicole E. Wagenblast" <nwagenbl at CS.Princeton.EDU> 
To: "Talks (colloquium)" <talks at lists.cs.princeton.edu> 
Sent: Monday, September 28, 2015 2:49:42 PM 
Subject: [talks] Colloquium Speaker- Percy Liang Thurs Oct 1, 4:30pm 

Colloquium Speaker 
Percy Liang, Stanford University 
Thursday, October 1st- 12:30pm 
Computer Science 105 

Learning Hidden Computational Processes 

We are interested in prediction problems in which evaluating the learned function requires multiple intermediate steps of computation. One motivation is building a system that can answer complex questions: here the function would need to map "How many countries have held the Summer Olympics more than once?" to "3" by applying a sequence of aggregation and filtering operations on a database. In this talk, we examine two key machine learning problems that arise in this setting. First, how do we model the computational process? We argue that the classic paradigm of decoupling modeling from inference is inadequate, and we propose techniques that directly model the inference procedure. Second, learning is very difficult: in our example, the supervision "3" constrains the hidden computational process in a very indirect way. We propose methods that relax the output supervision in a parameterized way, and learn both the relaxation and model parameters jointly subject to an explici 
t computational constraint. Finally, we show some empirical progress on a new challenging question answering task. 

Percy Liang is an Assistant Professor of Computer Science at Stanford University (B.S. from MIT, 2004; Ph.D. from UC Berkeley, 2011). His research interests include (i) modeling natural language semantics, (ii) developing machine learning methods that infer rich latent structures from limited supervision, (iii) and studying the tradeoff between statistical and computational efficiency. He is a 2015 Sloan Research Fellow, 2014 Microsoft Research Faculty Fellow, a 2010 Siebel Scholar, and won the best student paper at the International Conference on Machine Learning in 2008. 

talks mailing list 
talks at lists.cs.princeton.edu 
To edit subscription settings or remove yourself, use this link: 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/talks/attachments/20150928/fec41ef5/attachment.html>

More information about the talks mailing list