BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.18.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CMSA
X-ORIGINAL-URL:https://cmsa.fas.harvard.edu
X-WR-CALDESC:Events for CMSA
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:20261021T140000
DTEND;TZID=America/New_York:20261021T150000
DTSTAMP:20261014T152454Z
CREATED:20260729T194008Z
LAST-MODIFIED:20261014T152454Z
UID:10004014-1792591200-1792594800@cmsa.fas.harvard.edu
SUMMARY:Local learning needs dendrites
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Riccardo Zecchina (Bocconi University) \nTitle: Local learning needs dendrites \nAbstract: I will present a learning scheme for recurrent networks in which nonlinear dendrites enable learning by generating and stabilizing task-relevant attractors within a representation manifold. The scheme is local in space and time and matches the performance of backpropagation through time on the same architecture\, while following a fundamentally different trajectory in weight space. Statistical physics reveals how dendritic gating and the geometry of the representation manifold support this alternative route to learning.
URL:https://cmsa.fas.harvard.edu/event/newtech_102126/
LOCATION:CMSA Room G10\, CMSA\, 20 Garden Street\, Cambridge\, MA\, 02138\, United States
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/2026/10/CMSA-NTM-Seminar-10.21.2026.docx-scaled.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20261028T140000
DTEND;TZID=America/New_York:20261028T150000
DTSTAMP:20261014T203530Z
CREATED:20260729T194034Z
LAST-MODIFIED:20261014T203530Z
UID:10004015-1793196000-1793199600@cmsa.fas.harvard.edu
SUMMARY:The IEANTN Project: Automation and Mathematical Understanding
DESCRIPTION:New Technologies in Mathematics Seminar \nSpeaker: Xinjie He\, UCLA \nTitle: The IEANTN Project: Automation and Mathematical Understanding \nAbstract: Explicit analytic number theory combines conceptual arguments with extensive bookkeeping and numerical computation\, often drawing on long chains of results across many papers. The Integrated Explicit Analytic Number Theory Network (IEANTN) aims to organize this literature into a living network whose dependencies and supporting evidence are explicit. \nIn this talk\, I will discuss how we redesigned IEANTN from its 1.0 version\, which put everything in a single Lean repository that was hard to maintain and rebuild as auto-formalization produces increasingly large proofs\, to its current 2.0 version\, which solves this problem by separating readable mathematical statements from verified proofs and recording different levels of justification. \nFinally\, I will discuss what we hope to automate and what we want to understand ourselves. By organizing the literature into a network\, we hope to make the mathematical ideas and relationships easier to see\, and leave the detailed bookkeeping to machines. \n 
URL:https://cmsa.fas.harvard.edu/event/newtech_102826/
LOCATION:Virtual
CATEGORIES:New Technologies in Mathematics Seminar
ATTACH;FMTTYPE=image/png:https://cmsa.fas.harvard.edu/media/2026/07/CMSA-NTM-Seminar-10.28.2026.docx-scaled.png
END:VEVENT
END:VCALENDAR