BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: From Specialists to Generalists: Inductive Biases o
 f Deep Learning for Higher Level Cognition
DTSTART:20220210T153000
DTEND:20220210T163000
DTSTAMP:20260510T081916Z
UID:31f1c26a59c6cbcde85b7409544315ebf726e74a47ffd09ab10826c3
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Anirudh Goyal - University of Montreal\nIC Faculty candida
 te\n\nAbstract\nA fascinating hypothesis is that human and animal intellig
 ence could be explained by a few principles (rather than an encyclopedic l
 ist of heuristics). If that hypothesis was correct\, we could more easily 
 both understand our own intelligence and build intelligent machines. Just 
 like in physics\, the principles themselves would not be sufficient to pre
 dict the behavior of complex systems like brains\, and substantial computa
 tion might be needed to simulate human-like intelligence. This hypothesis 
 would suggest that studying the kind of inductive biases that humans and a
 nimals exploit could help both clarify these principles and provide inspir
 ation for AI research and neuroscience theories. Deep learning already exp
 loits several key inductive biases\, and my work considers a larger list\,
  focusing on those which concern mostly higher-level and sequential consci
 ous processing. The objective of clarifying these particular principles is
  that they could potentially help us build AI systems benefiting from huma
 ns' abilities in terms of flexible out-of-distribution and systematic gene
 ralization\, which is currently an area where a large gap exists between s
 tate-of-the-art machine learning and human intelligence.\n\nBio\nAnirudh G
 oyal is a student of science advised by Prof. Yoshua Bengio. His current r
 esearch interests center around understanding how neural learners can comp
 ose and abstract their own representations in a way that can be used to be
 tter generalize to out of distribution samples. More concretely\, his work
  focuses on designing such models by incorporating in them strong but gene
 ral assumptions (inductive biases) that enable high-level reasoning about 
 the structure of the world. During his PhD\, he has spent time as a visiti
 ng researcher at UC Berkeley\, MPI Tuebingen and DeepMind. He was also one
  of the recipients of the 2021 Google PhD Fellowship in Machine Learning.
  \n\nMore information
LOCATION:https://epfl.zoom.us/j/62311794505?pwd=ZDFwOWk0ZWxBdEtMd0NUYmxQNz
 hMZz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR