BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ARNI - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:ARNI
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:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VTIMEZONE
TZID:UTC
BEGIN:STANDARD
TZOFFSETFROM:+0000
TZOFFSETTO:+0000
TZNAME:UTC
DTSTART:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20241011T113000
DTEND;TZID=America/New_York:20241011T130000
DTSTAMP:20260503T054614
CREATED:20240913T200808Z
LAST-MODIFIED:20241008T172933Z
UID:1049-1728646200-1728651600@arni-institute.org
SUMMARY:CTN: Brenden Lake
DESCRIPTION:Title: Meta-learning for more powerful behavioral modeling \nAbstract: Two modeling paradigms have historically been in tension: Bayesian models provide an elegant way to incorporate prior knowledge\, but they make simplifying and constraining assumptions; on the other hand\, neural networks provide great modeling flexibility\, but they make it difficult to incorporate prior knowledge. Here I describe how to get the best of both approaches through Behaviorally-Informed Meta-Learning (BIML). BIML allows for modeling behavior with flexible Transformers\, even with only minimal data\, by distilling Bayesian priors into neural networks and then further fine-tuning the networks on behavioral data. I’ll show some initial successes using BIML to model human concept learning\, resulting in superior fits by capturing behavioral heuristics and biases that violate simple Bayesian assumptions. At the end\, I would love to discuss how to overcome the challenges of interpreting this new class of models. \nZoom: https://columbiauniversity.zoom.us/j/93740145362?pwd=GgoanUbc3Kc4rWdux2doLOiciiAaO2.1\nmeeting ID: 937 4014 5362\npasscode: ctn
URL:https://arni-institute.org/event/ctn-brenden-lake/
LOCATION:Zuckerman Institute – L3-079\, 3227 Broadway\, New York\, NY\, 10027\, United States
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=UTC:20241011T133000
DTEND;TZID=UTC:20241011T150000
DTSTAMP:20260503T054614
CREATED:20241004T201714Z
LAST-MODIFIED:20241004T201723Z
UID:1089-1728653400-1728658800@arni-institute.org
SUMMARY:Continual Learning Working Group: Lindsay Smith
DESCRIPTION:Title: A Practitioner’s Guide to Continual Multimodal Pretraining \nReading: https://arxiv.org/pdf/2408.1447 \nZoom: https://columbiauniversity.zoom.us/j/97176853843?pwd=VLZdh6yqHBcOQhdf816lkN5ByIpIsF.1
URL:https://arni-institute.org/event/continual-learning-working-group-10/
LOCATION:CEPSR 620\, Schapiro 530 W. 120th St
END:VEVENT
END:VCALENDAR