Skip to content

Physics Colloquium

Why Systems Biology Shouldn’t Work… but Does… and What Heat Capacity Can Explain about Learning

Paul Wiggins
University of Washington

Abstract:

Despite an intensifying interest in applications of machine learning to the analysis of big data, fundamental questions remain about the mechanisms of learning: (i) How can immensely complex models ever learn from small datasets? (ii) What is the physics of learning and (iii) are there universal properties in learning processes? In this talk, I will elaborate on a long-discussed analogy between Bayesian statistics and statistical mechanics. This correspondence reveals a surprisingly simple answer to these three questions by analogy, in the well known physics of the heat capacity. Finally, I will discuss how these insights can be used to design new learning algorithms.

Monday, April 8, 2019 at 3:30pm to 4:30pm

Science & Engineering Building, 307
1414 Circle Dr, Knoxville, TN 37996

Event Type

Lectures & Presentations

Topic

Science

Audience

Current Students, Faculty & Staff

Website

http://www.phys.utk.edu/colloquium.html

Department
Physics and Astronomy
Contact Name

Department of Physics and Astronomy

Contact Email

physics@utk.edu

Contact Phone

974-3342

Subscribe
Google Calendar iCal Outlook

Recent Activity