BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CMSA - ECPv6.16.3//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:20190310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20191103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20200308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20201101T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20210314T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20211107T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20200928T090000
DTEND;TZID=America/New_York:20200928T121300
DTSTAMP:20260710T112302
CREATED:20230707T111622Z
LAST-MODIFIED:20250409T192348Z
UID:10001223-1601283600-1601295180@cmsa.fas.harvard.edu
SUMMARY:CMSA Math-Science Literature Lecture: From Deep Learning to Deep Understanding
DESCRIPTION:Harry Shum (Tsinghua University) \nTitle: From Deep Learning to Deep Understanding \nAbstract: In this talk I will discuss a couple of research directions for robust AI beyond deep neural networks. The first is the need to understand what we are learning\, by shifting the focus from targeting effects to understanding causes. The second is the need for a hybrid neural/symbolic approach that leverages both commonsense knowledge and massive amount of data. Specifically\, as an example\, I will present some latest work at Microsoft Research on building a pre-trained grounded text generator for task-oriented dialog. It is a hybrid architecture that employs a large-scale Transformer-based deep learning model\,  and symbol manipulation modules such as business databases\, knowledge graphs and commonsense rules. Unlike GPT or similar language models learnt from data\, it is a multi-turn decision making system which takes user input\, updates the belief state\, retrieved from the database via symbolic reasoning\, and decides how to complete the task with grounded response. \nTalk chair: Shing-Tung Yau \nVideo
URL:https://cmsa.fas.harvard.edu/event/cmsa-math-science-literature-lecture_shum/
LOCATION:Virtual
CATEGORIES:Event,Math Science Literature Lecture Series,Public Lecture,Special Lectures
ATTACH;FMTTYPE=image/jpeg:https://cmsa.fas.harvard.edu/media/Lecture_Shum-pdf.jpeg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20200928T123000
DTEND;TZID=America/New_York:20200928T140000
DTSTAMP:20260710T112302
CREATED:20230707T111141Z
LAST-MODIFIED:20250328T201235Z
UID:10000141-1601296200-1601301600@cmsa.fas.harvard.edu
SUMMARY:CMSA Math-Science Literature Lecture: A personal story of the 4D Poincare conjecture
DESCRIPTION:Michael Freedman (Microsoft – Station Q) \nTitle: A personal story of the 4D Poincare conjecture \nAbstract:  The proof of PC4 involved the convergence of several historical streams.  To get started: high dimensional manifold topology (Smale)\, a new idea on how to study 4-manifolds (Casson)\, wild “Texas” topology (Bing). Once inside the proof: there are three submodules: Casson towers come to life (in the sense of reproduction)\, a very intricate explicit shrinking argument (provided by Edwards)\, and the “blind fold” shrinking argument (which in retrospect is in the linage of Brown’s proof of the Schoenflies theorem). Beyond those mentioned: Kirby\, Cannon\, Ancel\, Quinn\, and Starbird helped me understand my proof. I will discuss the main points and how they fit together. \nTalk Chair: Peter Kronheimer \nVideo
URL:https://cmsa.fas.harvard.edu/event/cmsa-math-science-literature-lecture_freedman/
LOCATION:Virtual
CATEGORIES:Event,Math Science Literature Lecture Series,Public Lecture,Special Lectures
ATTACH;FMTTYPE=image/jpeg:https://cmsa.fas.harvard.edu/media/Lecture_Freedman-1-pdf.jpeg
END:VEVENT
END:VCALENDAR