BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:187@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20260318T100000
DTEND;TZID=Asia/Kolkata:20260318T110000
DTSTAMP:20260316T080518Z
URL:https://cds.iisc.ac.in/events/cds-kiac-seminar-cds-102-18th-march-repr
 esentations-in-deep-learning-and-the-brain/
SUMMARY:CDS-KIAC {Seminar} @ CDS: #102: 18th\, March "Representations in De
 ep Learning and the Brain"
DESCRIPTION:We welcome you to CDS-KIAC talk on 18th March 2026 (Wednesday).
  The details are as below:\n\n\n\nSpeaker : Prof. Ambuj Singh \, UCSB\nTit
 le : Representations in Deep Learning and the Brain\nDate and Time : March
  18\, 2026: 10:00 AM\nVenue : # 102\, CDS Seminar Hall\n\n\n\nABSTRACT:\nR
 ecent progress in brain reconstruction has shown that visual and semantic 
 information can be decoded from fMRI into high-level representation spaces
 . In this talk\, we outline a broader research direction centered on repre
 sentation alignment as a unifying principle for brain modeling. First\, we
  discuss ongoing efforts to construct a shared\, aligned brain representat
 ion space that maps multiple subjects into a common geometry. Rather than 
 treating each subject or dataset independently\, this framework aims to fo
 rmalize subject-agnostic alignment and improve data efficiency through str
 uctured adapters. Second\, we describe extensions beyond fMRI to M/EEG\, e
 xploring whether heterogeneous modalities can be integrated into the same 
 representational space despite differences in spatial and temporal resolut
 ion. This raises foundational questions about what aspects of neural geome
 try are modality-invariant. Finally\, we broaden the perspective to task-d
 ependent representations and comparisons with modern AI systems\, includin
 g vision and language models. By studying representation structure\, align
 ment\, and geometry across biological and artificial systems\, we aim to b
 etter understand how task demands shape internal spaces and where human an
 d machine representations diverge.\n\nBIOGRAPHY:\nAmbuj K. Singh is a Dist
 inguished Professor of Computer Science at the University of California\, 
 Santa Barbara\, with a part-time appointment in the Biomolecular Science a
 nd Engineering Program. He received a B.Tech. degree from the Indian Insti
 tute of Technology\, Kharagpur\, and a PhD degree from the University of T
 exas at Austin. His research interests are broadly in the areas of machine
  learning\, network science\, and chemistry/biology. He has published abou
 t 300 technical papers over his career. He has led several multidisciplina
 ry projects including UCSB’s Information Network Academic Research Cente
 r funded by the Army\, Interdisciplinary Graduate Education Research and T
 raining (IGERT) program on Network Science funded by the NSF\, and the Mul
 tidisciplinary University Research Initiative (MURI) on Network Science of
  Teams funded by the US Army. His research has also been funded by the Nat
 ional Institute of Health and the Defense Threat Reduction Agency. He has 
 graduated over 50 graduate students over his career\, including over 30 Ph
 D students.\n\nHost Faculty: Dr. Danish Pruthi\, CDS\n\n\n\nALL ARE WELCOM
 E
CATEGORIES:Events,Talks
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20250318T100000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR