Abstract of FKI-201-94

Document-Name:  fki-201-94.ps.gz
Title:		SEMILINEAR PREDICTABILITY MINIMIZATION PRODUCES 
                ORIENTATION SENSITIVE EDGE DETECTORS
Authors:	Juergen Schmidhuber 
                Bernhard Foltin
Revision-Date:	1994/12/24 
Category:	Technical Report (Forschungsberichte Künstliche Intelligenz)
Abstract:	Static real world images are processed by a computationally
                simple  and  biologically plausible  version of  the recent
                predictability  minimization   algorithm  for  unsupervised
                redundancy  reduction.  Without a  teacher and  without any
                significant pre-processing, the system automatically learns
                to generate  orientation  sensitive  edge  detectors in the
                first (semilinear) layer.
Keywords:	predictability  minimization, redundancy  reduction,
		unsupervised learning, edge  detectors,
		orientation  sensitivity
Size:		7 pages
Language:	English
ISSN:		0941-6358
Copyright:	The ``Forschungsberichte Künstliche Intelligenz''
		series includes primarily preliminary publications,
		specialized partial results, and supplementary
		material. In the interest of a subsequent final
		publication these reports should not be copied. All
		rights and the responsability for the contents of the
		report are with the authors, which would appreciate
		critical comments.

Gerhard Weiss