Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!uunet!husc6!rutgers!ames!aurora!labrea!decwrl!decvax!ucbvax!KL.SRI.COM!Laws
From: Laws@KL.SRI.COM (Ken Laws)
Newsgroups: comp.ai.digest
Subject: Re: Neural Networks & Unaligned fields
Message-ID: <12331701930.42.LAWS@KL.SRI.Com>
Date: Thu, 3-Sep-87 13:01:52 EDT
Article-I.D.: KL.12331701930.42.LAWS
Posted: Thu Sep  3 13:01:52 1987
Date-Received: Sat, 5-Sep-87 16:57:23 EDT
References: <277@ndmath.UUCP>
Sender: usenet@ucbvax.BERKELEY.EDU
Reply-To: AIList-Request@SRI.COM
Organization: The ARPA Internet
Lines: 33
Approved: ailist@stripe.sri.com

The current networks will generally fail to recognize shifted patterns.
All of the recognition networks I have seen (including the optical
implementations) correlate the image with a set of templates and then
use a winner-take-all subnetwork or a feedback enhancement to select
the best-matching template.  Vision researchers were doing this kind
of matching (for character recognition, with the character known to
be centered in the visual field) back in the 50s and early 60s.  Position
independence was then added by convolving the image and template, essentially
performing the match at every possible shift.  This was rather expensive,
so Fourier, Hough, and hierarchical matching techniques were introduced.
Then came edge detection, shape description, and many other paradigms.
We don't have all the answers yet, but we've come a long way from the
type of matching currently implemented in neural networks.

The advantage of the networks, particularly those implemented in analog
hardware, is speed.  IF you have a problem for which alignment is known,
or IF you have time or hardware to try all possible alignments, or IF
your network is complex enough to store all templates at a sufficient
number of shifts, neural networks may be able to give you an off-the-shelf 
recognizer that bypasses the need to research all of the pattern recognition
literature of the last decade.

I suspect that the above conditions will actually hold in a fair number
of engineering situations.  Indeed, many of these applications have already
been identified by the signal processing community.  Neural networks offer
a trainable alternative to DSP or acoustic convolution chips.  Where rules
and explanations are appropriate, designers will use expert systems; otherwise
they will neural networks and similar systems.  Only the most difficult
and important applications will require development of customized reasoning
systems such as numerical or object-oriented simulations.

					-- Ken
-------