Robert Batterman - Deep Learning, Correlations, and the Statistics of Natural Imagesnull, Robert W. Batterman (University of Pittsburgh)
1117 Cathedral of Learning - 11th Floor
University of Pittsburgh, 4200 Fifth Avenue
Pittsburgh 15260
United States
This event is available both online and in-person
Organisers:
Details
The Center for Philosophy of Science at the University of Pittsburgh invites you to join us for our Lunch Time Talk. Attend in person at 1117 Cathedral of Learning or visit our live stream on YouTube at https://www.youtube.com/channel/UCrRp47ZMXD7NXO3a9Gyh2sg.
LTT: Robert Batterman
Friday, October 18 @ 12:00 pm - 1:30 pm EDT
Title: Deep Learning, Correlations, and the Statistics of Natural Images
Abstract: In this paper I will highlight certain connections between Deep Neural Networks (DNNs) and Renormalization Group methods in statistical physics. I will suggest that some of these similarities can be exploited to understand why some DNNs can be so successful. Specifically, I will suggest that DNNs generalize as well as they do because their training allows them to discover/recover certain remarkably robust statistical regularities present in their (diverse) training data sets.
Can’t make it in-person? This talk will available online through the following:
Zoom: https://pitt.zoom.us/s/94223992589
YouTube at https://www.youtube.com/channel/UCrRp47ZMXD7NXO3a9Gyh2sg.
Registration
No
Who is attending?
No one has said they will attend yet.
Will you attend this event?