BEGIN:VCALENDAR
PRODID:-//planitpurple.northwestern.edu//iCalendar Event//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
CLASS:PUBLIC
BEGIN:VTIMEZONE
TZID:America/Chicago
TZURL:http://tzurl.org/zoneinfo-outlook/America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:0
DTSTART;TZID=America/Chicago:20260526T130000
DTEND;TZID=America/Chicago:20260526T140000
DTSTAMP:20260523T140139Z
SUMMARY:CS Seminar: Deep Learning as a Natural Science: From Neurons to Scaling Laws (Amil Dravid)
UID:642600@northwestern.edu
TZID:America/Chicago
DESCRIPTION:Tuesday / CS Seminar May 26 / 1:00 PM Hybrid / Mudd 3514  Speaker Amil Dravid\, UC Berkeley  Talk Title Deep Learning as a Natural Science: From Neurons to Scaling Laws  Abstract  "As neural networks grow larger\, they increasingly resemble complex systems with systematic behavior rather than isolated engineered artifacts. This is reflected in neural scaling laws\, which show that performance follows a precise power law as a function of model size\, data\, and compute. Yet\, we still lack a principled scientific understanding of how these models organize information internally.  In this talk\, I will describe an approach to studying neural networks as scientific objects\, drawing on ideas from neuroscience and statistical physics. I will focus on neurons that respond to similar inputs across independently trained models of the same modality — for example\, neurons that fire for similar words across language models or similar objects and textures across vision models. We find that the population of shared neurons grows as a power law with model size\, but represents a shrinking fraction of the overall population. We account for this trend with a simple theoretical model\, which also predicts a polarization effect: as models grow\, shared neurons become increasingly selective for specific concepts\, such as code or visual textures\, while the remaining neurons become less selective and encode multiple features. We then test this prediction in large-scale language and vision models. I will conclude with a case study showing how neuron selectivity can guide targeted data selection to improve training. Together\, these results suggest that scaling laws are not restricted to external model behavior; they also describe regularities in how neural networks are organized internally."  Biography Amil Dravid is a third-year PhD student in computer science at UC Berkeley\, advised by Alyosha Efros. His research develops tools for understanding the internal structure of deep learning systems\, with the goal of informing the design of more effective algorithms and models. He previously earned his BS in Computer Science from Northwestern University. His research is supported by the U.S. Department of Energy Computational Science Graduate Fellowship.  Research Areas: Deep learning\, computer vision\, natural language processing  --- Zoom Link  Panopto Link
LOCATION:Mudd Hall ( formerly Seeley G. Mudd Library)\, 3514\, 2233 Tech Drive\, Evanston\, IL 60208
TRANSP:OPAQUE
URL:https://planitpurple.northwestern.edu/event/642600
CREATED:20250910T050000Z
STATUS:CONFIRMED
LAST-MODIFIED:20260520T211307Z
PRIORITY:0
BEGIN:VALARM
TRIGGER:-PT10M
ACTION:DISPLAY
DESCRIPTION:Reminder
END:VALARM
END:VEVENT
END:VCALENDAR