BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ARNI - ECPv6.16.3//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:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=UTC:20240322T150000
DTEND;TZID=UTC:20240322T170000
DTSTAMP:20260609T155353
CREATED:20240319T234436Z
LAST-MODIFIED:20240320T000555Z
UID:699-1711119600-1711126800@arni-institute.org
SUMMARY:Animal Behavior Video Analysis Working Group
DESCRIPTION:Title: Brain Decodes Deep Nets\nPresenter: Jianbo Shi\, PhD\nGRASP Laboratory\nComputer and Information Science\nUniversity of Pennsylvania\n \nAbstract: We developed a surprising usage of brain encoding: using a brain fMRI prediction model to draw a picture of how a deep net processes information onto a brain.  Our tool provides a detailed analysis of large pre-trained vision models by mapping them onto the brain\, thus exposing their hidden layers and channels.   Our results show how different training methods matter: they lead to remarkable differences in hierarchical organization and scaling behavior. It also provides insight into finetuning: how large pre-trained models change when adapting to new datasets. \n  \n\nJoin Zoom Meeting:\nhttps://columbiauniversity.zoom.us/j/93542681364?pwd=eFlZSkhGY0JHZGlHSk8zSVRYdHRSZz09 \nMeeting ID: 935 4268 1364\nPasscode: 645004
URL:https://arni-institute.org/event/animal-behavior-video-analysis-working-group-5/
LOCATION:CSB 453\, Mudd Building\, 500 W 120th Street
END:VEVENT
END:VCALENDAR