[VIRTUAL] Spring 2020 GRASP Seminar: Pratik Chaudhari, University of Pennsylvania, "Learning with Few Labeled Data"

ABSTRACT

The relevant limit for machine learning is not N → infinity but instead N → 0, the human visual system is proof that it is possible to learn categories with extremely few samples; humans do not need N = million images to distinguish edible mushrooms from poisonous ones in the wild. This ability is the result of having seen millions of other objects. The first part of the talk will discuss algorithms to adapt representations of deep neural networks to new categories given few labeled data. The second part will exploit a formal connection of thermodynamics and machine learning to characterize such adaptation and understand the fundamental limits of representation learning. This theory leads to algorithms for transfer learning that come with guarantees on the classification performance on the target task.

Presenter's biography

Pratik Chaudhari is an Assistant Professor in Electrical and Systems Engineering and Computer and Information Science at the University of Pennsylvania. He is a member of the GRASP Laboratory. From 2018-19, he was a Senior Applied Scientist at Amazon Web Services and a post-doctoral scholar in Computing and Mathematical Sciences at the CalTech. Pratik received his PhD (2018) in Computer Science from UCLA, his Master's (2012) and Engineer's (2014) degrees in Aeronautics and Astronautics from MIT and his Bachelor’s degree (2010) from IIT Bombay. He was a part of nuTonomy Inc. (now Aptiv) from 2014-16.

Location

Philadelphia, PA 19104
United States

Presenter

Pratik Chaudhari