Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!samsung!zaphod.mps.ohio-state.edu!wuarchive!mit-eddie!media-lab!minsky
From: minsky@media-lab.MEDIA.MIT.EDU (Marvin Minsky)
Newsgroups: comp.ai.neural-nets
Subject: Re: Which learning algorithm is best for scale/rotation invariant input?
Message-ID: <3519@media-lab.MEDIA.MIT.EDU>
Date: 2 Oct 90 02:32:24 GMT
References: <kilmer.653677625@sysp1> <reiner.654779094@lennox>
Reply-To: minsky@media-lab.media.mit.edu (Marvin Minsky)
Organization: MIT AI, Cambridge MA
Lines: 6

And be sure to read the original classic -- Pitts and McCulloch 1947,
reprinted in W.S.McCulloch's "Embodiments of Mind," MIT press book.
Although it was from the pre-computer age, it has nice clear
explanation of the relevant invariant Haar measure theory.  I don't
recall any good analysis therein of how to prune off the irrelevant
parts of the group to make things converge.