Humans and animals have a natural ability to autonomously learn and quickly adapt to their surroundings throughout their lives. How can we design machines that do the same? In this talk, Emtiyaz Khan will present Bayesian principles to bridge such gaps between humans and machines. He will show the Bayesian learning rule that unifies a wide range of machine-learning algorithms as special cases. The rule also gives rise to a dual perspective to measure the sensitivity to future changes. He will argue that it is the key to build machines that adapt as quickly as humans.
Bio:
Emtiyaz Khan (also known as Emti) is a (tenured) team leader at the RIKEN center for Advanced Intelligence Project (AIP) in Tokyo where he leads the Approximate Bayesian Inference Team. Previously, he was a postdoc and then a scientist at Ecole Polytechnique Fédérale de Lausanne (EPFL), where he also taught two large machine learning courses and received a teaching award. He finished his PhD in machine learning from University of British Columbia in 2012.
The main goal of Emti’s research is to understand the principles of learning from data and use them to develop algorithms that can learn like living beings. For more than 10 years, his work has focused on developing Bayesian methods that could lead to such fundamental principles. The approximate Bayesian inference team now continues to use these principles, as well as derive new ones, to solve real-world problems.
Date and Time:
Friday, November 15, at 15 pm CEST.
Join the Zoom Meeting:
https://cispa-de.zoom-x.de/j/65058577038?pwd=yiVSoQ080gyEeJpQcUxIcTlmeql2Ys.1
Meeting ID: 650 5857 7038
Passcode: +h2w2+