Cornell University

This is a past event. Its details are archived for historical purposes.

The contact information may no longer be valid.

Please visit our current events listings to look for similar events by title, location, or venue.

Seminar @ Cornell Tech: Jiajun Wu

Wednesday, April 10, 2019 at 11:00am to 12:00pm

Cornell Tech, Bloomberg 165 2 West Loop Road, NY NY 10044

"Learning to see the physical world"

Human intelligence is beyond pattern recognition. From a single image, we're able to explain what we see, reconstruct the scene in 3D, predict what's going to happen, and plan our actions accordingly. In this talk, I will present our recent work on physical scene understanding---building versatile, data-efficient, and generalizable machines that learn to see, reason about, and interact with the physical world. The core idea is to exploit the generic, causal structure behind the world, including knowledge from computer graphics, physics, and language, in the form of approximate simulation engines, and to integrate them with deep learning. Here, deep learning plays two major roles: first, it learns to invert simulation engines for efficient inference; second, it learns to augment simulation engines for constructing powerful forward models. I'll focus on a few topics to demonstrate this idea: building scene representation for both object geometry and physics; learning expressive dynamics models for planning and control; perception and reasoning beyond vision.

 

 

Subscribe
Google Calendar iCal Outlook
Event Type

Seminar

Departments

Cornell Tech - NYC

Hashtag

#CornellTech

Speaker

Jiajun Wu

Speaker Affiliation

Massachusetts Institute of Technology

Disability Access Information

Available Upon Request

Recent Activity