No subject

unido!tumult.informatik.tu-muenchen.de!schmidhu@uunet.UU.NET unido!tumult.informatik.tu-muenchen.de!schmidhu at uunet.UU.NET
Thu Jul 7 16:58:37 EDT 1988


 
Received: by tumult.informatik.tu-muenchen.de (1.2/4.81)
	id AA10801; Thu, 7 Jul 88 16:58:37 -0200
Date: Thu, 7 Jul 88 16:58:37 -0200
From: Juergen Schmidhuber <schmidhu at tumult>
Message-Id: <8807071458.AA10801 at tumult.informatik.tu-muenchen.de>
To: INS_ATGE at JHUVMS.BITNET, connectionists at cs.cmu.edu
Subject: Re:  Fractal Representations of Neural Networks Responses
Cc: schmidhu at tumult.informatik.tu-muenchen.de


I would like to ask a related question: Has there been any research on
recognizing fractal objects with neural nets? The first thing that
most neural networks do to some input is to apply a distributing
transformation. At first glance this should greatly simplify the
task of correlating the whole object to its parts (one might think
of some measure of self-similarity) and then doing the classification.

Juergen Schmidhuber



More information about the Connectionists mailing list