Personal tools
You are here: Home Events ANC/DTC Seminar: Dr. Jörg Lücke, University of Frankfurt

ANC/DTC Seminar: Dr. Jörg Lücke, University of Frankfurt

Representational Learning of Sensory Data Components

What
When Nov 08, 2011
from 11:00 AM to 12:00 PM
Contact Name Peggy Seriès
Add event to calendar vCal
iCal

In the nervous system of humans and animals, sensory data are represented as combinations of elementary data components. While for data such as sound waveforms the elementary components combine linearly, other data can better be modeled by non-linear forms of component superpositions. I motivate and discuss two models of component extraction: one using standard linear superpositions of basis functions (similar to standard sparse coding) and one using non-linear superpositions.  Crucial for the applicability of both models are efficient learning procedures. I briefly introduce a novel training scheme (truncated variational EM) and show how it can be applied to probabilistic generative models. For linear and non-linear models the scheme efficiently infers the basis functions as well as the level of sparseness and data noise. Furthermore, I discuss the close relation of the approach to neural processing.  In large-scale applications to image patches, we show results on the statistics of the inferred parameters of linear and non-linear models. Differences between the models are discussed, and both models are compared to results of standard approaches in the literature and to experimental findings.  Finally, I briefly discuss other recent projects of my group including learning in a model that takes explicit component occlusions into account.