- Date: Monday September 30, 2019
- Time: From 7:00 pm To 9:00 pm
- Location: Lake Hills Library
- Address: 15590 Lake Hills Blvd, Bellevue, Washington 98007
- Facebook Page: www.facebook.com/events/500275660531507/
Understanding the Visual World by Interacting with it
This is a talk following by a Q&A
Moderated by Seattle SUTA (Sharif University of Technology Association)
Speaker: Dr Roozbeh Mottaghi
Bio: Roozbeh Mottaghi is a Senior Research Scientist at Allen Institute
for AI. Prior to joining AI2, he was a post-doctoral researcher at the
Computer Science Department at Stanford University. He obtained his PhD in Computer Science in 2013 from University of California, Los Angeles. His research is mainly focused on Computer Vision and Machine Learning.
Abstract: In recent years, deep learning models have demonstrated
tremendous improvement in core computer vision problems such as image classification and object detection. Now, it might be the time to move one step forward and tackle problems that require higher levels of reasoning. My focus in this talk will be on three main topics: (1) Physics-based image understanding, where the idea is to learn physics of the world from visual data, (2) Learning by interaction, where the idea is to train an autonomous agent by interacting with the environment, (3) Learning from intelligent agents, where we mount sensors on a dog and try to learn its behavior.