BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Brain - ECPv6.15.18//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Brain
X-ORIGINAL-URL:https://brain.uci.edu
X-WR-CALDESC:Events for Brain
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20220313T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20221106T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20230312T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20231105T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20240310T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20241103T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20230321T110000
DTEND;TZID=America/Los_Angeles:20230321T120000
DTSTAMP:20260421T140546
CREATED:20221006T220515Z
LAST-MODIFIED:20230214T170733Z
UID:10000357-1679396400-1679400000@brain.uci.edu
SUMMARY:Pierre Baldi\, Ph.D. - NEW DATE
DESCRIPTION:CNLM Colloquium UCI Spotlight Series \nJoin the CNLM in a hybrid colloquium featuring Dr. Pierre Baldi\, Distinguished Professor in the Department of Computer Science and Director of the Institute for Genomics and Bioinformatics at UC Irvine. \nThis event will be held in-person in the Herklotz Conference Center and virtually via Zoom. \n \n\n\n\nThe quest for how the brain learns \n\n\n\n\n\n\nWe will first showcase two cutting-edge applications of modern Artificial Intelligence (AI) in biomedical imaging and in reasoning. These applications\, as well as most modern AI applications (e.g.\, ChatGPT\, AlphaFold\, AlphaGO\, Google Translate\, Self-Driving Cars) are based on deep learning\, a modern rebranding of neural networks\, or connectionist methods\, dating back to the 1980s\, or even the 1950s.  We will then briefly review the neuroscience-inspired\, tortuous\, historical path that has led to deep learning\, and the key discoveries made along the way\, highlighting the synergies and discrepancies between neuroscience and deep learning. One key conclusion is that approximate gradient descent is essential for learning. However\,  the standard gradient descent algorithm of deep learning called backpropagation  is not biologically-plausible for multiple reasons. We will examine these reasons one-by-one and identify biologically-plausible solutions for each one of them. In particular\, we will introduce and demonstrate a general class of neural architectures and learning algorithms capable of learning from data in a largely unsupervised and asynchronous manner\, without the need for symmetric connectivity.
URL:https://brain.uci.edu/event/pierre-baldi-ph-d/
LOCATION:CNLM Herklotz Conference Center and Virtually via Zoom
CATEGORIES:Faculty,Scientific,Staff,Students
ATTACH;FMTTYPE=image/png:https://brain.uci.edu/wp-content/uploads/sites/49/2021/08/pierre-baldi-01-400x267-1.png
ORGANIZER;CN="UCI Center for the Neurobiology of Learning and Memory":MAILTO:memory@uci.edu
END:VEVENT
END:VCALENDAR