View movie

View thumbnails
Run time: 56:17

Play / Download (help)

(228 MB)Ogg Video
(234 MB)512Kb MPEG4
(2.1 GB)MPEG2

Resources

Redwood Center for Theoretical NeuroscienceUrs Köster: Towards Multi-Layer Processing of Natural Images (2006)

This is a talk given at the Redwood Center for Theoretical Neuroscience, UC Berkeley on November 11, 2006 by Urs Köster from the University of Helsinki.

Abstract:
Since the discovery of Simple and Complex cells in primary visual cortex, which have easily visualized receptive fields, efforts have been made to build models that show the emergence of similar features using unsupervised learning techniques applied to natural image data. Here we discuss recent work on extending single layer models to give rise to complex cell receptive fields. We proceed to describe a novel method called “Score Matching” for the estimation of multi-layer statistical models and the application to modeling of primary visual cortex.


This movie is part of the collection: Open Source Movies

Producer: Redwood Center for Theoretical Neuroscience
Audio/Visual: sound, color
Keywords: Theoretical Neuroscience; Redwood Center; UC Berkeley; Seminar; Vision
Contact Information: Kilian Koepsell Redwood Center for Theoretical Neuroscience University of California Helen Wills Neuroscience Institute 132 Barker, MC #3190 Berkeley, CA 94720-3190

Individual Files

Be the first to write a review
Downloaded 321 timesReviews