Copy Link
Add to Bookmark
Report
AIList Digest Volume 5 Issue 209
AIList Digest Friday, 4 Sep 1987 Volume 5 : Issue 209
Today's Topics:
Query - Researchers in Neural/Connectionist Robotics &
Neural Networks Simulations in Smalltalk/LISP/(Prolog) &
Neural Networks & Unaligned fields,
Database - AI Expert Magazine Source Code,
AI Tools - Commercial Planning/Scheduling Systems
----------------------------------------------------------------------
Date: Thu, 3 Sep 87 09:05 PDT
From: nesliwa%telemail@ames.arpa (NANCY E. SLIWA)
Subject: Researchers in neural/connectionist robotics?
A colleague of mine is attempting to organize a session for the
American Controls Conference in neural/connectionist approaches/applications
to robotics (other that strictly image processing). Could anyone
suggest the names/addresses/phone numbers of researchers in this area?
Particularly other than Kuperstein, Jorgensen, and Pellionisz.
Thanks in advance.
Nancy Sliwa
MS 152D
NASA Langley Research Center
Hampton, VA 23665-5225
(804)865-3871
nancy@grasp.cis.upenn.edu
nesliwa%telemail@orion.arpa
------------------------------
Date: 2 Sep 87 20:11:21 GMT
From: plx!titn!jordan@sun.com (Jordan Bortz)
Subject: NEURAL NETWORKS SIMULATIONS IN Smalltalk/LISP/(prolog)
Has anyone implemented any neural network simulations in any of the
above languages?
Huh?
Jordan
--
=============================================================================
Jordan Bortz Higher Level Software 1085 Warfield Ave Piedmont, CA 94611
(415) 268-8948 UUCP: (decvax|ucbvax|ihnp4)!decwrl!sun!plx!titn!jordan
=============================================================================
------------------------------
Date: 3 Sep 87 21:53:45 GMT
From: hao!boulder!mikek@husc6.harvard.edu (Mike Kranzdorf)
Subject: Re: NEURAL NETWORKS SIMULATIONS IN Smalltalk/LISP/(prolog)
>Has anyone implemented any neural network simulations in any of the
>above languages?
Try P3 from UCSD Institute of Cognitive Science (LISP)
Contact David Zipser
You can find out more about it from the PDP books (Ch. 13 I believe)
--mike
------------------------------
Date: 2 Sep 87 19:18:10 GMT
From: ihnp4!inuxc!iuvax!ndmath!milo@ucbvax.Berkeley.EDU (Greg Corson)
Subject: Neural Networks & Unaligned fields
Ok, here's a quick question for anyone who's getting into Neural Networks.
If you setup the type of network described in BYTE this month, or the
type used in the program recently posted to the net, what happens if you
feed it an input image that is not aligned right?
For example, in the Byte article they demonstrate correct recall of an image
corrupted by randomly flipping a number of bytes, simulating "noise". What
would happen if they just shifted the input image one or two bits to the left?
Would the network still recognize the pattern?
Greg Corson
...seismo!iuvax!ndmath!milo
------------------------------
Date: Thu 3 Sep 87 10:01:52-PDT
From: Ken Laws <Laws@KL.SRI.Com>
Reply-to: AIList-Request@SRI.COM
Subject: Re: Neural Networks & Unaligned fields
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
------------------------------
Date: 3 Sep 87 15:41:53 GMT
From: hao!boulder!mikek@husc6.harvard.edu (Mike Kranzdorf)
Subject: Re: Neural Networks & Unaligned fields
I am not familiar with the net in Byte, but I assume it is a two layer net,
like the one that was posted. If this is the case, shifted patterns will
not be recognized. It takes at least three layers for a net to have an
internal representation of the structure of an input pattern. A good
overview paper describing these kinds of conditions can be found in the
IEEE ASSP (Acoustics, Speech, and Signal Processing) Magazine April 1987,
Volume 4, Number 2, "An Introduction to Computing with Neural Nets" by
Richard P. Lippmann. The article focuses on catagorizers, but is
informative about nets in general.
--mike
------------------------------
Date: 2 Sep 87 15:04:26 GMT
From: ecsvax.uucp!burgin@mcnc.org (Robert Burgin)
Subject: AI Expert Magazine Source Code
I believe that the source code from AI EXPERT magazine is
available on a New York City BBS:
303-273-3989
1200-N-8-1
--rb
------------------------------
Date: Wed, 2 Sep 87 12:03 PDT
From: nesliwa%telemail@ames.arpa (NANCY E. SLIWA)
Subject: Commercial planning/scheduling systems survey
I recently asked for information about any commercially available products
that provided computer assistance to planning/scheduling problems. I had
far more requests for a copy of the responses than actual responses, so
I'm posting the responses I did receive:
> Date: Wed, 12 Aug 87 11:40 EST
> From: KENYON%cgi.com@relay.cs.net
> Subject: Planning/Scheduling software
>
> This may not be what you had in mind, but Carnegie Group (in Pittsburgh)
> offers Knowledge Craft, an extremely powerful tool with which several
> advanced planning and scheduling systems have been built. One of the
> founders of the company is Mark Fox, who has done considerable research
> in the area of applying AI to planning and scheduling problems.
>
> If you're interested in a toolkit, rather than a canned (and probably
> restrictive) program, I'd suggest that you give Jay Ferguson, the
> Knowledge Craft product manager a call; he can give you more technical
> information on how the product might fill your needs.
>
> Our address here is:
>
> Carnegie Group Inc
> 650 Commerce Court at Station Square
> Pittsburgh, PA 15219
> (412) 642 6900
>
> Jeff Kenyon
> Educational Services
> Carnegie Group
>
> P.S. I know, I work for them, so I'm biased. But it really is a great
> product.
>
> Date: Tue, 11 Aug 87 14:57:55 BST
> Message-Id: <714.8708111357@soay.aiva.ed.ac.uk>
> To: nesliwa <@orion:nesliwa@telemail>
> Subject: Your Commercial Planning/scheduling software? survey
>
>
> My research is in the area of AI planning systems. I like the idea of doing
> a survey of commercially available systems, and would like to hear the
> results of your survey.
>
> A company called Consilium produces a Work In Progress Tracking system
> which ties in with some scheduling software. Address:
>
> Consilium
> 1945 Charleston Rd.
> Mountain View CA 94043
> (415) 940 1400
>
>
> -- Mark Drummond
>
> ARPA: med%uk.ac.ed.aiva@ucl.cs
> JANET: med@uk.ac.ed.aiva
> Paper Mail:
> AI Applications Institute
> University of Edinburgh
> 80 South Bridge
> Edinburgh, U.K. EH1 1HN
>
>
> Date: Mon, 10 Aug 87 14:17 EDT
> From: Scott Garren <garren@STONY-BROOK.SCRC.Symbolics.COM>
> Subject: Planning Systems
>
> There is a very good package called XPM from:
>
> Expert Management Systems
> 2432 West Peoria, Suite 1050
> Phoenix, Arizona 85029
> 602-870-1001
>
> Date: Mon, 10 Aug 87 13:20:32 PDT
> From: Michael Shafto <shafto@ames-aurora.arpa>
>
> The AI Magazine, Volume VII, Number 5 (Winter, 1986)
> ISSN 0738-4602 [this references the Callistro Project and OPGEN]
>
> Best regards,
>
> Mike Shafto
>
> Date: Friday, 21 August 1987 14:19:27 EDT
> From: Perry.Zalevsky@isl1.ri.cmu.edu
> Subject: Request for Planning and Scheduling Software
>
> Nancy,
> I saw your request for commercially available planning and scheduling
> software and was wondering if you could pass the information that you
> received on to me. Did you get info about InterFase or Factrol? Send me mail
> and I can respond about the above two packages if you want.
>
> Perry Zalevsky
I am following up these pointers with requests to the referenced companies
for more specific information (also to companies I was already aware of that
provided such products). Since there seems to be some interest in this area,
I will post a summary of these responses when available.
If any of you that did not previously respond have some additional pointers,
I'd sincerely appreciate your relaying them to me!
Nancy Sliwa
MS 152D
NASA Langley Research Center
Hampton, VA 23665-5225
(804)865-3871
nancy@grasp.cis.upenn.edu
nesliwa%telemail@orion.arpa
------------------------------
End of AIList Digest
********************
