How Do Our ML Models Succeed?

Speaker

Shibani Santurkar, Computer Science at MIT

Machine learning models today attain impressive accuracy on many benchmark tasks. Yet, these models also remain remarkably brittle—small perturbations of natural inputs can completely degrade their performance. 

Why is this the case?

In this talk, we take a closer look at this brittleness, and examine how it can, in part, be attributed to the fact that our models often make decisions very differently from humans. Viewing neural networks as feature extractors, we study how features extracted by neural networks may diverge from those used by humans, and how adversarially robust models seem to make progress towards bridging this gap.
Shibani Santurkar’s website

You are invited to a scheduled Zoom meeting. Zoom is Yale’s audio and visual conferencing platform.

• Join the Zoom
• Or Telephone：203-432-9666 (2-ZOOM if on-campus) or 646 568 7788  
• Password: 24
• Meeting ID: 958 6320 8758    
• International numbers available

For H.323 and SIP information for video conferencing units