BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260518T020034EDT-3615gdN9pn@132.216.98.100
DTSTAMP:20260518T060034Z
DESCRIPTION:DIC-ISC-CRIA Seminar at UQAM\n\nSpeaker: Yoshua Bengio\, Univer
 sité de Montreal\n\nWebinar Link\n\nAbstract:\n\nHumans are very good at “
 out-of-distribution” generalization (compared to current AI systems). It w
 ould be useful to determine the inductive biases they exploit and translat
 e them into machine-language architectures\, training frameworks and exper
 iments. I will discuss several of these hypothesized inductive biases. Man
 y exploit notions in causality and connect abstractions in representation 
 learning (perception and interpretation) with reinforcement learning (abst
 ract actions). Systematic generalizations may arise from efficient factori
 zation of knowledge into recomposable pieces. This is partly related to sy
 mbolic AI (aas seen in the errors and limitations of reasoning in humans\,
  as well as in our ability to learn to do this at scale\, with distributed
  representations and efficient search). Sparsity of the causal graph and l
 ocality of interventions -- observable in the structure of sentences -- ma
 y reduce the computational complexity of both inference (including plannin
 g) and learning. This may be why evolution incorporated this as 'conscious
 ness.” I will also suggest some open research questions to stimulate furth
 er research and collaborations. \n\nBio:\n\nRecognized worldwide as one of
  the leading experts in artificial intelligence\, Yoshua Bengio is most kn
 own for his pioneering work in deep learning\, earning him the 2018 A.M. T
 uring Award\, “the Nobel Prize of Computing\,” with Geoffrey Hinton and Ya
 nn LeCun.\n\nHe is a Full Professor at Université de Montréal\, and the Fo
 under and Scientific Director of Mila – Quebec AI Institute. He co-directs
  the CIFAR Learning in Machines & Brains program as Senior Fellow and acts
  as Scientific Director of IVADO.  He is also an alumnus of the Centre for
  Intelligent Machines.\n\nEvent Link\n
DTSTART:20220217T153000Z
DTEND:20220217T163000Z
LOCATION:CA\, ZOOM
SUMMARY:Conscious processing\, inductive biases and generalization in deep 
 learning
URL:https://www.mcgill.ca/cim/channels/event/conscious-processing-inductive
 -biases-and-generalization-deep-learning-337640
END:VEVENT
END:VCALENDAR