BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:A Function Approximation Perspective on Neural Representations
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260910T040032Z
UID:tag:localist.com\,2008:EventInstance_34367105291142
DTSTART:20201023T173000Z
DTEND:20201023T183000Z
DESCRIPTION:IACS seminars a free and open to the public but registration is
  required.\n\nTalk Abstract: Activity patterns of neural populations in na
 tural and artificial neural networks constitute representations of data. T
 he nature of these representations and how they are learned are key questi
 ons in neuroscience and deep learning. In his talk\, Professor Pehlevan wi
 ll describe his group’s efforts in building a theory of representations 
 as feature maps leading to sample efficient function approximation. Kernel
  methods are at the heart of these developments. He will present applicati
 ons of his group's theories to deep learning and neuronal data.
LOCATION:
SUMMARY:A Function Approximation Perspective on Neural Representations
URL;VALUE=URI:https://events.seas.harvard.edu/event/a_function_approximatio
 n_perspective_on_sensory_representations
CATEGORIES:Colloquia / Seminar / Lecture
END:VEVENT
END:VCALENDAR