Max-Planck-Institut für Informatik
max planck institut
informatik
mpii logo Minerva of the Max Planck Society
 

MPI-INF or MPI-SWS or Local Campus Event Calendar

<< Previous Entry Next Entry >> New Event Entry Edit this Entry Login to DB (to update, delete)
What and Who
Title:Information Geometry of Learning Systems
Speaker:Nihat Ay
coming from:University of Leipzig
Speakers Bio:
Event Type:Talk
Visibility:D1, D2, D3, D4, D5, RG1, SWS, MMCI
We use this to send out email in the morning.
Level:Public Audience
Language:English
Date, Time and Location
Date:Thursday, 14 June 2018
Time:14:00
Duration:60 Minutes
Location:Saarbr├╝cken
Building:E1 5
Room:029
Abstract
In my introduction, I will review prime concepts of information theory and information geometry and highlight their relevance for machine learning. Most importantly, information geometry allows us to interpret a learning system as a parametrised geometric object in which the learning process takes place. This interpretation is the basis of various highly successful applications of information-geometric methods to learning systems, including, for instance, the natural gradient method.

Intelligent behaviour can only emerge through sensorimotor interactions, incorporating the brain, the body, and the environment. This crucial understanding has many far-reaching implications and led to the field of embodied intelligence. What does this understanding mean for learning? I am firmly convinced that the efficiency of learning strongly depends on the coupling of the system's control architecture, its brain, with its embodiment constraints. In the main part of my talk, I will outline an information-geometric approach to
such a coupling and present results on the design of embodied systems with concise control architectures. This formalises the notion of "cheap control" within the field of embodied intelligence. While most of the results are based on the class of restricted Boltzmann machines, I will conclude with ongoing research related to more general architectures. In particular, I will present initial results on the natural gradient method for deep learning in embodied agents.

Contact
Name(s):Connie Balzert
Video Broadcast
Video Broadcast:NoTo Location:
Tags, Category, Keywords and additional notes
Note:
Attachments, File(s):

Created:Connie Balzert/MPI-INF, 06/08/2018 12:44 PM Last modified:Uwe Brahm/MPII/DE, 06/14/2018 07:01 AM
  • Connie Balzert, 06/08/2018 12:44 PM -- Created document.