Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for March 06, 2019
-
CS Colloquium: Behnam Neyshabur (New York University) - Why Do Neural Networks Learn?
Wed, Mar 06, 2019 @ 09:00 AM - 10:00 AM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Behnam Neyshabur, New York University
Talk Title: Why Do Neural Networks Learn?
Series: CS Colloquium
Abstract: Neural networks used in practice have millions of parameters and yet they generalize well even when they are trained on small datasets. While there exists networks with zero training error and a large test error, the optimization algorithms used in practice magically find the networks that generalizes well to test data. How can we characterize such networks? What are the properties of networks that generalize well? How do these properties ensure generalization?
In this talk, we will develop techniques to understand generalization in neural networks. Towards the end, I will show how this understanding can help us design architectures and optimization algorithms with better generalization performance.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Behnam Neyshabur is a postdoctoral researcher in Yann LeCun's group at New York University. Before that, he was a member of Theoretical Machine Learning program lead by Sanjeev Arora at the Institute for Advanced Study (IAS) in Princeton. In summer 2017, he received a PhD in computer science at TTI-Chicago where Nati Srebro was his advisor. He is interested in machine learning and optimization and his primary research is on optimization and generalization in deep learning.
Host: Haipeng Luo
Location: Ronald Tutor Hall of Engineering (RTH) - 109
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium:Sida Wang (Princeton University) - Learning Adaptive Language Interfaces Through Interaction
Wed, Mar 06, 2019 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Sida Wang, Princeton University
Talk Title: Learning Adaptive Language Interfaces Through Interaction
Series: CS Colloquium
Abstract: The interactivity and adaptivity of natural language have the potential to allow people to better communicate with increasingly AI-driven computer systems. However, current natural language interfaces are mostly static and fall short of their potential. In this talk, I will cover two systems that can quickly learn from interactions, adapt to users, and simultaneously give feedback so that users can adapt to the system. The first system learns from scratch from users in real time. The second starts with a programming language and then learns to naturalize the programming language by interacting with users. Finally, I will present how these ideas can be combined to build a natural language interface for data visualization and discuss my work on modeling interactive language learning more rigorously.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Sida Wang is a research instructor at Princeton University and Institute for Advanced Study working in the areas of natural language processing and machine learning. He holds a Ph.D. in computer science from Stanford University and a B.A.Sc. from the University of Toronto. He received an outstanding paper award at ACL 2016 and the NSERC Postgraduate Scholarship.
Host: Joseph Lim
Location: Ronald Tutor Hall of Engineering (RTH) - 115
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CAIS Seminar: Lindsay Young (University of Chicago) - Social Network Analysis and Artificial Intelligence: Methodological Partners in the Study of HIV Prevention and Risk Online
Wed, Mar 06, 2019 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Lindsay Young, University of Chicago
Talk Title: Social Network Analysis and Artificial Intelligence: Methodological Partners in the Study of HIV Prevention and Risk Online
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: As transmitters of information and progenitors of behavioral norms, social networks are critical mechanisms of HIV prevention and risk in impacted populations like men who have sex with men (MSM), people who inject drugs (PWID), and homeless youth. Today, widespread use of online social networking technologies (e.g., Facebook, Instagram, Twitter) yield unprecedented amounts of relational and communication data far richer than anything previously collected in offline (physical) network settings. However, parsing these complex data into tractable insights and solutions requires an innovative and flexible computational toolkit that extends beyond traditional approaches. In this talk, Dr. Young will discuss her ongoing efforts to unpack how HIV prevention and risk manifest in the Facebook networks of young MSM using a hybrid of computational methods that include social and semantic network analysis and machine learning approaches for textual analysis and predictive modeling. She will conclude with a discussion of the practical implications of this work and outstanding challenges that require further exploration.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Dr. Lindsay Young is a NIH Pathway to Independence Award Postdoctoral Fellow at the University of Chicago Department of Medicine and Chicago Center for HIV Elimination (CCHE). Trained as a social scientist and network methodologist, she now applies those perspectives to understand the social and communicative contexts of HIV risk and prevention among young sexual minorities and other vulnerable populations. She is particularly interested in how online social network data can be leveraged for behavioral research and interventions.
Host: Milind Tambe
Location: James H. Zumberge Hall Of Science (ZHS) - 252
Audiences: Everyone Is Invited
Contact: Computer Science Department
