Hi all,
Our next speaker is James Wright from Microsoft Research NYC. The talk will take place on July 28, at AA6214, 13:45. Hope to see many of there!
Title: Deep Learning for Predicting Human Strategic Behavior
Abstract: Predicting the behavior of human participants in strategic settings is an important problem in many domains. Most existing work either assumes that participants are perfectly rational, or attempts to directly model each participant's cognitive processes based on insights from cognitive psychology and experimental economics. In this work, we present an alternative, a deep learning approach that automatically performs cognitive modeling without relying on such expert knowledge. We introduce a novel architecture that allows a single network to generalize across different input and output dimensions by using matrix units rather than scalar units, and show that its performance significantly outperforms that of the previous state of the art, which relies on expert-constructed features.
Bio: James Wright's research focuses on problems at the intersection of economics, behavioral modeling, and machine learning, with a focus on modeling and predicting human behavior in strategic settings. Prior to joining Microsoft Research NYC, he completed a Ph.D. in Computer Science at the University of British Columbia, where he was advised by Kevin Leyton-Brown.
Dima
Afficher les réponses par date
Hi all,
A kind reminder that this talk is today! Please note that the room has changed, it will take place at *AA3195*.
Dima
On Wed, 26 Jul 2017 at 10:10 Dzmitry Bahdanau dimabgv@gmail.com wrote:
Hi all,
Our next speaker is James Wright from Microsoft Research NYC. The talk will take place on July 28, at AA6214, 13:45. Hope to see many of there!
Title: Deep Learning for Predicting Human Strategic Behavior
Abstract: Predicting the behavior of human participants in strategic settings is an important problem in many domains. Most existing work either assumes that participants are perfectly rational, or attempts to directly model each participant's cognitive processes based on insights from cognitive psychology and experimental economics. In this work, we present an alternative, a deep learning approach that automatically performs cognitive modeling without relying on such expert knowledge. We introduce a novel architecture that allows a single network to generalize across different input and output dimensions by using matrix units rather than scalar units, and show that its performance significantly outperforms that of the previous state of the art, which relies on expert-constructed features.
Bio: James Wright's research focuses on problems at the intersection of economics, behavioral modeling, and machine learning, with a focus on modeling and predicting human behavior in strategic settings. Prior to joining Microsoft Research NYC, he completed a Ph.D. in Computer Science at the University of British Columbia, where he was advised by Kevin Leyton-Brown.
Dima
We are starting right now!
On Fri, 28 Jul 2017 at 09:31 Dzmitry Bahdanau dimabgv@gmail.com wrote:
Hi all,
A kind reminder that this talk is today! Please note that the room has changed, it will take place at *AA3195*.
Dima
On Wed, 26 Jul 2017 at 10:10 Dzmitry Bahdanau dimabgv@gmail.com wrote:
Hi all,
Our next speaker is James Wright from Microsoft Research NYC. The talk will take place on July 28, at AA6214, 13:45. Hope to see many of there!
Title: Deep Learning for Predicting Human Strategic Behavior
Abstract: Predicting the behavior of human participants in strategic settings is an important problem in many domains. Most existing work either assumes that participants are perfectly rational, or attempts to directly model each participant's cognitive processes based on insights from cognitive psychology and experimental economics. In this work, we present an alternative, a deep learning approach that automatically performs cognitive modeling without relying on such expert knowledge. We introduce a novel architecture that allows a single network to generalize across different input and output dimensions by using matrix units rather than scalar units, and show that its performance significantly outperforms that of the previous state of the art, which relies on expert-constructed features.
Bio: James Wright's research focuses on problems at the intersection of economics, behavioral modeling, and machine learning, with a focus on modeling and predicting human behavior in strategic settings. Prior to joining Microsoft Research NYC, he completed a Ph.D. in Computer Science at the University of British Columbia, where he was advised by Kevin Leyton-Brown.
Dima
lisa_seminaires@iro.umontreal.ca
-
Dzmitry Bahdanau