Max-Planck-Institut für Informatik
max planck institut
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:Accelerated Learning of Probabilistic Data Models for Large-Scale Applications
Speaker:Jörg Lücke
coming from:University of Oldenburg
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
Date, Time and Location
Date:Thursday, 14 June 2018
Duration:60 Minutes
Building:E1 5
Probabilistic models are powerful and very general mathematical tools for a range of Machine Learning tasks including clustering, classification, denoising, inpainting, detection, tracking, source separation or image and sound understanding. The key theoretical and practical question is how probabilistic data models can effectively and efficiently be learned from data. The question applies to elementary data models used, e.g., for clustering and classification as well as to advanced and novel data models that enable novel applications.

I will first give an introduction to the task of data clustering, and will introduce two well-known algorithms: k-means and Expectation Maximization (EM) for Gaussian Mixture Models (GMMs). The properties, relations and computational complexities of the two algorithms will be explained and discussed. By using the example of a GMM as probabilistic model, I will then proceed by introducing truncated variational approximations for accelerated learning. Following their introduction, I will discuss the theoretical foundations of truncated approximations and their generalization to graphical models with discrete latents.

My presentation will close with applications of variational learning to standard and advanced data models. Highlights will include sublinear clustering of large datasets, `black-box' learning, large-scale deep models for semi-supervised learning, and unsupervised learning algorithms for visual, acoustic and medical data.

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

Created:Connie Balzert/MPI-INF, 06/08/2018 12:41 PM Last modified:Uwe Brahm/MPII/DE, 06/14/2018 07:01 AM
  • Connie Balzert, 06/08/2018 12:41 PM -- Created document.