BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
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:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20220313T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20221106T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20221005T120000
DTEND;TZID=America/New_York:20221005T133000
DTSTAMP:20260405T141645
CREATED:20220909T132756Z
LAST-MODIFIED:20220909T132756Z
UID:7287-1664971200-1664976600@seasevents.nmsdev7.com
SUMMARY:ASSET Seminar: Learning with Small Data\, Pratik Chaudhari (University of Pennsylvania)
DESCRIPTION:Abstract:\nThe 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. This talk will discuss steps towards building such systems and it is structured in three parts. The first part will discuss algorithms to adapt representations of deep networks to new categories with few labeled data. The second part will discuss when such adaptation works well and when it does not. It will develop a method to compute the optimal distance between two learning tasks and algorithmic tools to learn tasks that are far away from each other. The third part will discuss how make the optimal use of unlabeled data to learn a task. \nThis talk will discuss results from the following papers.\n1. An Information-Geometric Distance on the Space of Tasks. Yansong\nGao\, Pratik Chaudhari. ICML 2021.\nPaper: https://arxiv.org/abs/2011.00613\, Code: https://github.com/Yansongga/An-Information-Geometric-Distance-on-the-Space-of-Tasks\n2. Model Zoo: A Growing “Brain” That Learns Continually. Rahul\nRamesh\, Pratik Chaudhari. ICLR 22.\nPaper: https://arxiv.org/abs/2106.03027. Code:\nhttps://github.com/rahul13ramesh/MultitTask_ModelZoo\n3. Deep Reference Priors: What is the best way to pretrain a model?. Yansong Gao\, Rahul Ramesh\, and Pratik Chaudhari. ICML 22.\nPaper: https://arxiv.org/abs/2202.00187\, Code: https://github.com/grasp-lyrl/deep_reference_priors
URL:https://seasevents.nmsdev7.com/event/asset-seminar-tba-pratik-chaudhari-university-of-pennsylvania/
LOCATION:Levine 307\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Seminar
ORGANIZER;CN="Computer and Information Science":MAILTO:cherylh@cis.upenn.edu
END:VEVENT
END:VCALENDAR