Select a calendar:
Filter January Events by Event Type:
Conferences, Lectures, & Seminars
Events for January
-
CAIS Seminar: Kobi Gal (Ben-Gurion University) - Supporting Interactions in Online Groups: A New Challenge for AI
Wed, Jan 16, 2019 @ 04:15 PM - 05:15 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Kobi Gal, Ben-Gurion University of the Negev and Harvard University
Talk Title: Supporting Interactions in Online Groups: A New Challenge for AI
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: Advances in network technologies and interface design are enabling group activities of varying complexities to be carried out, in whole or in part, over the internet (e.g., citizen science, Massive Online Open Courses [MOOC] and questions-and-answers sites). The need to support these highly diverse interactions brings new and significant challenges to AI: how to design efficient representations for describing online group interactions, how to provide incentives that keep participants motivated and productive, and how to provide useful, non-intrusive information to system designers to help them decide whether and how to intervene with the group's work. Dr. Gal will describe two ongoing projects that address these challenges in the wild, and discuss the potential societal and ethical implications of this work.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Dr. Ya'akov (Kobi) Gal is a faculty member of the Department of Software and Information Systems Engineering at the Ben-Gurion University of the Negev, and an associate of the School of Engineering and Applied Sciences at Harvard University. His work investigates representations and algorithms for making decisions in heterogeneous groups comprising both people and computational agents. He has worked on combining artificial intelligence algorithms with educational technology towards supporting students in their learning and teachers to understand how students learn. He has published over 60 papers in highly refereed venues on topics ranging from artificial intelligence to the learning and cognitive sciences.
Host: Milind Tambe
Location: Grace Ford Salvatori Hall Of Letters, Arts & Sciences (GFS) - 106
Audiences: Everyone Is Invited
Contact: Computer Science Department
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor. -
CS Colloquium: Zhou Yu (UC Davis) - Grounding Reinforcement Learning with Real-World Dialog Applications
Thu, Jan 17, 2019 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Zhou Yu, UC Davis
Talk Title: Grounding Reinforcement Learning with Real-World Dialog Applications
Series: CS Colloquium
Abstract: Recently with the wide-spread of conversational devices, more and more people started to realize the importance of dialog research. However, some of them are still living in a simulated world, using simulated data such as Facebook bAbl. In this talk, we emphasize that dialog research needs to be grounded with the users' real need. We introduce three user-centered task-oriented dialog systems that are trained by reinforcement learning algorithms. The first system is a dialog systems that utilized reinforcement learning to interleave social conversation and task conversation to promote movies more effectively. The second system is a sentiment adaptive bus information search system. It uses
sentiment as immediate reward to help the end-to-end RL dialog
framework to converge faster and better. The trained dialog policy will also have a user friendly effect. It would adapt to user's sentiment when choosing dialog action templates. For example, the policy will pick template that provides more detailed instructions when user is being negative. This is extremely useful for customer service dialog systems where users frequently get angry. The third system is a task-oriented visual dialog systems. It uses a hierarchical reinforcement learning to track multimodal dialog states
and decide among sub tasks of whether to ask more information or just give an answer. Such system can complete the task more successfully and effectively. We are conducting a further experiment to deploy the system as a shopping assistant.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Zhou is an Assistant Professor at the Computer Science Department in UC Davis. She received her PhD in the Language Technology Institute under School of Computer Science, Carnegie Mellon University. She was recently featured in Forbes as 2018 30 under 30 in Science. Her team won Amazon Alexa Prize 2018 with $500,000 award. (https://developer.amazon.com/alexaprize) She as also received research awards and gifts from various companies, such as Intel, Tencent, Cisco and Bosh.
Host: Fei Sha
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
