BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ARNI - ECPv6.17.4//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://arni-institute.org
X-WR-CALDESC:Events for ARNI
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20270314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20271107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20260917T140000
DTEND;TZID=America/New_York:20260917T170000
DTSTAMP:20260908T192821Z
CREATED:20260908T192800Z
LAST-MODIFIED:20260908T192821Z
UID:2647-1789653600-1789664400@arni-institute.org
SUMMARY:Speaker: Pratik Chaudhari ARNI WG Multi-resource-cost optimization of neural network models
DESCRIPTION:Pratik Chaudhari \n\n\n\n\n\n\nPratik Chaudhari is an Associate Professor in Electrical and Systems Engineering and Computer and Information Science at the University of Pennsylvania. He is also a Scholar at Amazon Web Services. Pratik is a core member of the GRASP Laboratory. From 2018-19\, he was a Senior Applied Scientist at Amazon Web Services and a Postdoctoral Scholar in Computing and Mathematical Sciences at Caltech. He received his PhD in Computer Science from UCLA\, and his Master’s and Engineer’s degrees in Aeronautics and Astronautics from MIT. Pratik was a part of NuTonomy Inc. (now Hyundai-Aptiv Motional) from 2014-16. He is the recipient of the Amazon Machine Learning Research Award\, NSF CAREER award and the Intel Rising Star Faculty Award.\n\n\n\n\n\n\nDate: September 17\, 2026 \nLocation: ZI L7-119 \nTime: 2:00pm \nTitle: How Has Learning Shaped Our World? \nAbstract: \nAlmost every sub-field of science\, engineering and business is rapidly adopting deep learning technology. I will argue that it is really the properties of natural data derived from the physical world that makes deep networks so effective. Correlations of typical inputs (images\, text\, sounds\, and even tabular data) are “sloppy”\, i.e.\, they exhibit geometric decay. Sloppy systems are neither perfectly robust nor perfectly tuned but instead exhibit a wide range of sensitivities that allows them to strike a balance between robustness and adaptability. This is what enables deep networks to generalize to new data. \nI will show that the training process in deep learning explores a remarkably low dimensional manifold\, as low as three. Networks with a wide variety of architectures\, sizes\, optimization and regularization methods lie on the same manifold. Networks being trained on different tasks (e.g.\, different subsets of ImageNet) using different methods (e.g.\, supervised\, transfer\, meta\, semi and self-supervised learning) also lie on the same low-dimensional manifolds. This is proof that there exist neural architectures with extremely few parameters—as few as 50—that can reproduce the predictions of networks with millions of weights. Architectures that exploit this phenomenon can reduce the energy required to build deep learning systems by multiple orders of magnitude. \nI will show that typical tasks that we perform with deep learning are highly redundant functions of their inputs. Many perception tasks\, from visual recognition\, semantic segmentation\, optical flow\, depth estimation\, to vocalization discrimination\, can be predicted extremely well regardless of whether data is projected in the principal subspace where it varies the most\, some intermediate subspace with moderate variability—or the bottom subspace where data varies the least. Any feature set is near-sufficient for most tasks. Ontogenetic learning refines neural circuitry to improve this feature set. I will argue that this redundancy could be—the serendipitous—consequence of the sensory apparatus of an organism adapting to a changing stream of ecological tasks. \nPrinciples that inform learning in artificial agents can also shed light upon learning in biological organisms. To that end\, I will describe results on developing visual perception for autonomous robots (flying platforms and quadrupeds) that operate in different environments (harsh daylight as well as night-time\, indoors and outdoors)\, at very high speeds (without motion blur) and with very little energy. \nZoom Link: Upon request @ arni@columbia.edu
URL:https://arni-institute.org/event/speaker-pratik-chaudhari-arni-wg-multi-resource-cost-optimization-of-neural-network-models/
LOCATION:Zuckerman Institute – L7-119\, 3227 Broadway\, New York\, NY\, 10027\, United States
END:VEVENT
END:VCALENDAR