BEGIN:VCALENDAR
PRODID:-//Grails iCalendar plugin//NONSGML Grails iCalendar plugin//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260606T091417Z
DTSTART;TZID=America/New_York:20241011T153000
DTEND;TZID=America/New_York:20241011T173000
SUMMARY:Colin Klein - Transformers\, Representational Structure\, and the Language of Thought
UID:20260611T195243Z-iCalPlugin-Grails@philevents-web-bd7db559-gt5qm
TZID:America/New_York
LOCATION: University of Pittsburgh\, 4200 Fifth Avenue\, Pittsburgh\, United States\, 15260
DESCRIPTION:<p>The Center for Philosophy of Science at the University of Pittsburgh invites you to join us for our 65th Annual Lecture Series Talk.&nbsp\;Attend in person in room 1008 in the Cathedral of Learning (10th Floor)&nbsp\; or visit our live stream on YouTube at&nbsp\;<a rel="noopenerdata-cke-saved-href="https://www.youtube.com/channel/UCrRp47ZMXD7NXO3a9Gyh2sg">https://www.youtube.com/channel/UCrRp47ZMXD7NXO3a9Gyh2sg</a>.</p>\n<p>The Annual Lecture Series\, the Center&rsquo\;s oldest program\, was established in 1960\, the year when Adolf Gr&uuml\;nbaum founded the Center. Each year the series consists of six to eight lectures\, about three quarters of which are given by philosophers\, historians\, and scientists from other universities.</p>\n\n<p><strong>ALS &ndash\;</strong><a data-cke-saved-href="https://researchportalplus.anu.edu.au/en/persons/colin-klein"><u>Colin Klein </u></a></p>\n<p>Friday\, October 11&nbsp\; @ 3:30 pm&nbsp\;-&nbsp\;6:00 pm&nbsp\;EDT</p>\n<p>1008 Cathedral of Learning&nbsp\;</p>\n<p><strong>Title:&nbsp\;Transformers\, Representational Structure\, and the Language of Thought</strong></p>\n<p><strong>Abstract:</strong></p>\n<p>Transformers are an extraordinarily powerful computational architecture\, applicable across a range of domains. They are\, notably\, &nbsp\;the computational foundation of contemporary Large Language Models (LLMs). &nbsp\;LLMs&rsquo\; facility with language have led many to draw analogies between LLMs and human cognitive processing. Drawing out the consequences of what seems like an innocuous step&mdash\;the need for positional encoding of the input to LLMs&mdash\;I argue that transformers are broad precisely because they have so little built-in representational structure. This naturally raises questions about the need for structured representations and what (if any) advantage they might have over mere representation of structure. I develop this in particular in the context of the contemporary revival of the Language of Thought hypothesis.</p>\n<p>YouTube at&nbsp\;<a data-cke-saved-href="https://www.youtube.com/channel/UCrRp47ZMXD7NXO3a9Gyh2sg">https://www.youtube.com/channel/UCrRp47ZMXD7NXO3a9Gyh2sg</a>.</p>
ORGANIZER;CN=Edouard Machery:
METHOD:PUBLISH
END:VEVENT
END:VCALENDAR
