Copy Link
Add to Bookmark
Report
Neuron Digest Volume 11 Number 50
Neuron Digest Tuesday, 31 Aug 1993 Volume 11 : Issue 50
Today's Topics:
Letter/Submission to Neuron Digest
Neural Dreams...
Ref: 1993 SCSC Paper
Request
Kohonen Software & Email Address
Benchmarks?
seeking a Director for a Center for Neuroscience at Boston Univ.
NevProp 1.16 Update Available
Neural hardware performance criteria
Commercial Neural Network Software
cybernetics
Help for signature verification
neural network society membership
neural network research centers
Send submissions, questions, address maintenance, and requests for old
issues to "neuron-request@psych.upenn.edu". The ftp archives are
available from psych.upenn.edu (130.91.68.31). Back issues requested by
mail will eventually be sent, but may take a while.
----------------------------------------------------------------------
Subject: Letter/Submission to Neuron Digest
From: David Kanecki <kanecki@cs.uwp.edu>
Date: Tue, 17 Aug 93 20:54:50 -0600
[[ Editor's Note: Thanks to David for this description. I'm sure many
readers will find it food for thought and may wish to correspond with him
about his work on the "classic" problem which AI tried to tackle 20-30
years ago. -PM ]]
~
August 17, 1993
Dear Peter,
If you wish, I can send a copy of my "Neural Chess" presentation text and a
copy of my "3D Neural Chess" presentation text.
Since, I last wrote you, I have made two other developments in Neural Chess
as 1) Development of 3d Neural Chess and 2) Completion of the first Neural
Chess study "The Use of 2D Neural Chess, an Intelligent, Thinking Computer
Program as an Aid to Compare Strategic/Personal Neural Processing". I would
like to submit the "3d Neural Chess" abstract and the "2d Neural chess"
study for publication in the Neuron Digest.
Also, I am unemployed and looking for employment in this or other science
fields. For employment correspondence or a copy of my current resume,
please contact me at 4410 19th Avenue, Kenosha, WI 53140, (414)- 654-7560
or by e-mail. Finally, I have set up the "Neural/Sim BBS" at
(414)-654-7560 that runs from 7pm to 7am CT, Monday through Friday.
Next, an overview of what I present is:
On intelligent, thinking systems I have developed four categories of
new systems and technologies as 1) 1992 - Module 1 - 2d Neural Chess - The
basis of intelligent, thinking systems; 2) 1993 - Module 2 - 3d Neural
Chess - The enhancement and next level in intelligent, thinking systems;
and 3) The ability to quantify strategic/ personal neural decision making;
and 4) High speed and high volume data analysis using the neural programs
to define "intelligent control processor systems".
Finally, any inquires or licences for the Neural Chess programs or high
speed and high volume data analysis (intelligent control processor system)
can be directed to: Peter Jansson, Attorney at Law, 245 Main St. Racine,
WI, (414)-632-6900
======== 3d Neural Chess Abstract ========
First, I have developed "3D Neural Chess". This is an enhancement of the
Neural Chess program that allows the computer to play chess in 3 dimensions
as x,y, and z and opposed to two dimensions as x and y as conventional
chess. Thus, the decision making is more complicated. The "3D Neural Chess"
paper was published in 1993 Summer Computer Simulation Conference Proceed-
ings. This application represents a major learning breakthrough in learning
and teaching applications and modules using the main program as the basis.
The abstract of the paper is as follows:
A Decision Support System for Simulation and Real Time Applications
as 3D Neural Chess
David H. Kanecki, A.C.S., Bio. Sci.
P.O. Box 26944
Wauwatosa, WI 53226-0944
In decision support systems, this 3d computer program covers a major break-
through in the importance of new software techniques and applications in
micro computing environments, palmtop computing. 3d neural chess includes
the whole decision space, while 2d neural chess includes a plane of the
decision space, and is only a partial support to the decision support
system. Based on my work and paper as "Simulation as an Intelligent, Think-
ing Computer Program as Neural Chess" that was presented at the 1992 SCSC
(Kanecki 1992a), I have developed a 3d Neural chess program that shows the
1) strength, 2) adaptability, and 3) learning of reasoning by sensation,
sensual reasoning. This decision support program was a 3 year outgrowth
from the Neural Chess program. The goals of the project were 1) Is sensual
reasoning universal, 2) How well could it work in the next dimensional
system?
In this paper, I will present the game environment of three dimensional
chess that the 3d chess program played. Also, I will desrcibe the conclu-
sions of a match against against a human opponent. Finally, I will describe
the cognitive theory proved in this project.
The decision support system as 3d neural chess is expandable to many other
physical systems. It can be used in accessible, portable micro systems in
various physical environments, terrain processing, navigation, and resource
planning applications (air, water, land, space). The computer programs
requires thousands of lines of programming and uses "no decision trees or
databases" and is based strictly on "sensual reasoning" by the neural
network. By additional logic models, the future applications mentioned can
be developed.
Keywords: Sensual reasoning, Decision Support Systems, 3D Neural Chess,
AI/KBS, Neural Networks, Terrain Processing, Robotics, Cognition, Intelli-
gent Thinking Computer Software, Resource Planning, Logistics, Atomic Mind,
Interaction Difference
<Published in the 1993 Summer Computer Simulation Conference Proceedings,
The Society for Computer Simulation, San Diego, CA >
======== 2d Neural Chess Study =========
With the neural chess program, I have been able to study the strategic and
personal neural processing of individuals based on the chess matches that
they have played. From this study, I have found measureable differences in
neural processing. The neural chess programs allow one to quantify these
differences as stated in the paper below:
The Use of 2D-Neural Chess,
an Intelligent, Thinking Computer Program,
as an Aid to Compare
Strategic/Personal Neural Processing
By
David H. Kanecki, A.C.S., Bio. Sci.
P.O. Box 26944
Wauwatosa, WI 53226-0944
Internet: kanecki@cs.uwp.edu
Neural/SIM BBS, (414)-654-7560, 7pm-7am ct, 300/1200 baud
With the use of the 2D-Neural Chess program, I was able to determine quan-
titative differences in various chess strategies. The study was done by
having the 2D Neural chess program generate a neural matrix that best
responded and adapted to a given chess match that was processed by the
program. The response and adaptation used a process called sensual reason-
ing (Kanecki 1992a). This process allows the computer to make a decision by
integrating its sensations in a method similar to biological organisms
(Kanecki 1992a).
The 2D Neural Chess program, represents a new development in emulating
intelligence and thinking. The program is unique in that it uses no data-
base or game trees. Instead, it uses real time neural update using a bio-
logical basis as its model (Kanecki 1990a). The basis of its decision
making, is the atomic neuron and atomic mind (Kanecki 1992a). The atomic
neuron sense and the atomic mind integrates and acts.
In the initial test matches of the program against a human opponent, the
program was able to defeat a human opponent (Kanecki 1991a). Also, the 2D-
Neural Chess program had learned how to defeat a human opponent in only
four games. In addition, the 2D-Neural Chess program is so responsive and
adaptive, it can continue to play a strong chess match even when an oppo-
nent deliberately makes an illegal move (Kanecki 1991a, Kanecki 1992a). In
addition, the Neural Chess program can explain in ordinary human written
language why it choose its move. Lastly, the 2D-Neural Chess program repre-
sents 10 years of research.
In this study using the 2D-Neural Chess program, I wanted to see if the
program could allow one to quantitatively determine if there was a differ-
ence in various chess strategies? To start the study, I selected 5 chess
strategies with 3 replicates of each strategy. Then, after each match, the
atomic neural values were sorted and collated by strategy, time interval,
and game result. Next, the data was analyzed for 3 major time intervals
using the chi square method. Finally, the data was normalized by dividing
the chi square value by the significant chi square value. Thus, any value
greater than 1.00 is significant. Also, any value greater than 2.00 is
highly significant and a value greater than 3.00 is extremely significant.
The results of the study are:
Strategy - Win/Loss Comparison
Move | KID GRU QID BER PIR
----------------------------------------------------------
5 | 0.18 0.14 0.72 0.96 0.04
11 | 0.33 1.41 1.21 2.11 0.20
18 | 4.14 10.15 2.33 5.51 0.59
In the table above, the abbreviations 'KID' is used to indicate that the
"King's Indian Defense" was used, 'GRU' is used to indicate that the
"Gruenfeld Defense" was used, 'BER' is used to indicate that the "Bern
Defense" was used, and 'PIR' is used to indicate that the "PIRC Defense"
was used. The word 'move' is used to indicate the ending time interval. The
three time intervals used were moves 0, initial atomic neuron states, to 5,
moves 6 to 11, and moves 12 to 18.
Two general comments can be made on various chess strategies. One, the
difference measure, the normalized chi square value, increased in each time
interval. Two, the difference measure reaches the significance threshold,
1.00, at different time intervals. For example, the 'KID' strategy reaches
the significance threshold at time interval 18, the 'GRU' strategy reaches
the significance threshold at time interval 11, the 'QID' strategy reaches
the significance threshold at time interval 11, and the 'BER' strategy
reaches the significance interval at time interval 11. The only exception
to the second statement, is the 'PIR' strategy. This strategy does not
reach the significance threshold in the time intervals studied.
The quantitative analysis that is afforded by sensual reasoning, allows one
to view increases and decreases in difference measures. Also, the quantita-
tive difference measure allows one to monitor changes in the neural system
as the atomic neuron and atomic mind. Finally, it shows how responsive and
adaptive neural systems are to solving neural processing problems, i.e.
chess strategies.
The game of chess was used as metaphor to study neural interaction in
decision making. An interesting observation made in this project, was that
the computing method was needed much more that the computing hardware. For
example, Neural Chess, later to be called 2D-Neural Chess, was originally
developed on an Osborne-1 with 64K RAM and running CP/M. Also, because of
the computing power of neural systems, the Osborne-1 Neural chess program
was able to make chess decisions in real time. Thus, a neural processing
method and computer used with proper neural architecture basis allows one
to study an aspect of human thought "in vitro".
[1992] Kanecki, D.H., "Simulation as an Intelligent, Thinking Computer
System as Neural Chess", Proceedings 1992 Summer Computer Simulation Con-
ference, The Society for Computer Simulation, pages 428-432.
[1991] Kanecki, D.H., "Neural Chess - Presentation of Findings", Neuron
Digest, Volume 7, Issue 39, July 8, 1991.
[1990] Kanecki, D.H., "Neural Chess: I have developed a program", Neuron
Digest, Volume 6, Issue 88, November 25, 1990.
------------------------------
Subject: Neural Dreams...
From: ttgrq@info.win.tue.nl (Andreas Gammel)
Date: Wed, 18 Aug 93 14:11:33 +0100
[[ Editor's Note: As long-time readers know, the Digest is for beginners
and sophisticates alike. This fellow does take the topic farther than
many of our day-to-day work... -PM ]]
Hello, my name is Andreas and I'm a newbie in the field of NN and this
list. If read a very nice book about it (back propagation, cascade
correlation, hopfield nets etc) and I'm thinking of writing some programs
for it. Any software (Dos, Unix, sources and ftp-sites) would be most
appreciated. Just email it to me.
I have a rather phylosofical topic..
I was wondering if it would be possible to let a Neural Net dream?
What I mean is this. Say we make a NN with 100 binary inputs and 1 binary
output. The input is a 10 x 10-grid representing some picture. The output
is an answer to the question "Does the picture show a house" for example.
We then train this NN to respond positivly to pictures of houses and
negatively to other pictures. Now this is al fine, it has been done
before... but I was wondering is it would be thinkable to REVERSE all
arrows in the trained NN so that the input becomes 1 bit (house? yes or
no) and the output becomes a 10x10 grid. (in other words the NN is
DREAMING about houses). I suspect that human dreaming works basicly the
same.
Would the output resemble a house? And if yes, to what extent? If it
works, could the same be achieved by using centerfolds instead of houses,
thereby creating a 'dirty mind' (for our younger list-members)
Bye for now
Andreas
ttgrq@info.win.tue.nl
------------------------------
Subject: Ref: 1993 SCSC Paper
From: David Kanecki <kanecki@cs.uwp.edu>
Date: Wed, 18 Aug 93 13:07:50 -0600
Dear Peter,
The complete reference for the 1993 SCSC paper is:
"A Decision Support System for Simulation and Real Time Applications as
3D Neural Chess", 1993 Summer Computer Simulation Conference Proceedings,
Published by the Society for Computer Simulation (SCS), San Diego, CA,
pages 289-294.
David H. Kanecki, A.C.S., Bio. Sci.
kanecki@cs.uwp.edu
------------------------------
Subject: Request
From: pmastin@vnet.IBM.COM
Date: Thu, 19 Aug 93 15:36:25 -0500
[[ Editor's Note: A common question, but I no longer have a common
answer. What are considered the better intro books now? -PM ]]
I am new to neural networks, but come from a background of logic
Programming. I am interested in learning algorthms, and have
heard NN are good for this purpose. Is there any lit. that
establishes this, that would be accessable to a neophyte like
myself? Thanks in advance for any answers.
Pete
------------------------------
Subject: Kohonen Software & Email Address
From: Steve Greig <steve@department-computer-studies.napier.ac.uk>
Date: Mon, 23 Aug 93 13:02:47 +0000
Dear All,
I'm looking for some source code for a Kohonen Self-Organizing Feature Map.
The language of the source code doesn't matter, just as long as it is clear
and comprehensible (comments!?). On second thoughts, assembler language would
not be much use. C/C++/Pascal/Oberon/Lisp/Scheme/Prolog/SML would be okay.
Also, does anyone know what Kohonen's email address is, or if he has one.
Thanks in advance,
Steve
- -----------------------------------------------------------------------------
Steve Greig email: steve@uk.ac.napier.dcs
Computer Studies Department
Napier University tel: +44-31-455-4285
219 Colinton Road fax: +44-31-455-7209
Edinburgh EH14 1DJ
Scotland
------------------------------
Subject: Benchmarks?
From: stjaffe@vaxsar.vassar.edu (steve jaffe)
Date: 23 Aug 93 14:20:40 -0500
[[ Editor's Note: I remember Scott Fahlman (at CMU?) was informally
collecting benchmarks, buty I haven't heard of those efforts for a couple
of years... -PM ]]
Does there exist a reasonably standard set of benchmark problems on which
to compare various algorithms with respect to speed, accuracy, ability to
generalize, etc.? Information sent to me via email will be summarized to
the digest.
Thanks.
Steve Jaffe
Math Dept, Vassar College, Poughkeepsie NY 12601
stjaffe@vaxsar.vassar.edu
------------------------------
Subject: seeking a Director for a Center for Neuroscience at Boston Univ.
From: Announce@retina.bu.edu (Boston University Center for Adaptive Systems)
Organization: Center for Adaptive Systems, Boston University, Boston, MA, USA
Date: 25 Aug 93 18:25:20 +0000
Boston University seeks to hire a tenured full professor
to serve as the Director of a new Center for Neuroscience
on its Charles River Campus. The director will take a
leadership role in hiring the core faculty of the center.
The director will also coordinate the development of a
graduate PhD granting program in neuroscience. Candidates
for director should have an exceptional international
reputation as an experimental neuroscientist, preferably
in behavioral neurophysiology or related areas. The
director should have a broad scholarly perspective in
neuroscience and demonstrated leadership skills with which
to build a world-class center. The director would also
coordinate the process of linking the center to the multiple
neuroscience-related resources that are already part of
Boston University. Candidates should send a complete
curriculum vitae and three letters of recommendation to
Neuroscience Search Committee, Department of Cognitive and
Neural Systems, Room 240, 111 Cummington Street, Boston
University, Boston, MA 02215. Boston University is an
Equal Opportunity/Affirmative Action employer.
------------------------------
Subject: NevProp 1.16 Update Available
From: Phil Goodman <goodman@unr.edu>
Date: Thu, 26 Aug 93 16:35:53 +0000
Please consider the following update announcement:
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
NevProp 1.16 corrects a bug in the output range of symmetric sigmoids and
one occuring when the number of testing is fewer than training cases.
These fixes are further described in the README.CHANGES file at the
UNR anonymous ftp, described below.
The UNR anonymous ftp host is 'unssun.scs.unr.edu', and the files are
in the directory 'pub/goodman/nevpropdir'.
Version 1.15 users can update 3 ways:
a. Just re-ftp the 'nevprop1.16.shar' file and unpack and 'make' np again.
(also available at the CMU machine, describe below.)
b. Just re-ftp (in "binary" mode) the DOS or MAC executable binaries
located in the 'dosdir' or 'macdir' subdirectories, respectively.
c. Ftp only the 'np.c' file provided, replacing your old version, then 'make'
d. Ftp only the 'np-patchfile', then issue the command
'patch < np-patchfile' to locally update np.c, then 'make' again.
New users can obtain NevProp 1.16 from the anonymous UNR anonymous ftp
as described in (a) or (b) above, or from the CMU machine:
a. Create an FTP connection from wherever you are to machine
"ftp.cs.cmu.edu". The internet address of this machine is
128.2.206.173, for those who need it.
b. Log in as user "anonymous" with your own ID as password.
You may see an error message that says "filenames may not
have /.. in them" or something like that. Just ignore it.
c. Change remote directory to "/afs/cs/project/connect/code".
NOTE: You must do this in a single operation. Some of the
super directories on this path are protected against outside
users.
d. At this point FTP should be able to get a listing of files
in this directory with "dir" & fetch the ones you want with "get".
(The exact FTP commands depend on your local FTP server.)
Version 1.2 will be released soon. A major new feature will be the option
of using cross-entropy rather than least squares error function.
Phil
___________________________
___________________________ Phil Goodman,MD,MS goodman@unr.edu
| __\ | _ \ | \/ || _ \ Associate Professor & CBMR Director
|| ||_// ||\ /||||_// Cardiovascular Studies Team Leader
|| | _( || \/ ||| _(
||__ ||_\\ || |||| \\ CENTER for BIOMEDICAL MODELING RESEARCH
|___/ |___/ || |||| \\ University of Nevada School of Medicine
Washoe Medical Center H1-166, 77 Pringle Way,
Reno, NV 89520 702-328-4867 FAX:328-4111
* * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
------------------------------
Subject: Neural hardware performance criteria
From: Heini Withagen <heiniw@sun1.eeb.ele.tue.nl>
Date: Fri, 27 Aug 93 14:37:13 +0100
Currently, several neural network chips are available, both commercially
and in laboratories. Choosing which of those chips best suits your
application can be difficult. At the moment, several criteria are
used to describe the performance of a chip, like Connections Per Second,
Connections Updates Per Second, etc. However, these criteria are very
rough and with these it is not possible to compare chips very well.
At our university, we have done some research to come up with better
criteria which take into account the (neural) architecture of the chip,
the speed, the sensitivity to non-idealities (like non-linear multipliers
in the case of an analog chip), etc.
With this posting, I am hoping to evoke some reactions to see if there
are people who are interested in this subject. Especially, reactions
from the commercial side would be welcome (Intel, Adaptive Solutions,
Hitachi, AT&T, etc.).
Greetings,
- --
Heini Withagen
Dep. of Elec. Engineering EH 9.29
Eindhoven University of Technology
P.O. Box 513 Phone: 31-40472366
5600 MB Eindhoven Fax: 31-40455674
The Netherlands E-mail: heiniw@eeb.ele.tue.nl
========================================================================
------------------------------
Subject: Commercial Neural Network Software
From: manallack_d%frgen.dnet@smithkline.com (NAME "David Manallack")
Date: Fri, 27 Aug 93 09:39:54 -0500
Dear Neuron Digest Readers
We are currently writing a chapter on Neural Networks in a book
titled 'Methods and Principles in Medicinal Chemistry'. The book
is targeted at medicinal chemists interested in modern methods of
molecular design. As you may be aware, networks have found various
uses in chemistry (e.g Quantitative Structure-Activity Relationships
(QSAR)), typically using back propagation algorithms.
The editors of the book have asked us to include an appendix
listing commercially available neural network software suitable
for use by medicinal chemists.
We would therefore like to request any interested readers to send
us the name, address and cost of any suitable software. A brief
description would also be appreciated.
David Manallack email: manallack_d%frgen.dnet@smithkline.com
David Livingstone email: livingstondj@smithkline.com
------------------------------
Subject: cybernetics
From: Harry Jerison <IJC1HJJ@MVS.OAC.UCLA.EDU>
Date: Fri, 27 Aug 93 17:29:00 -0800
Dear friends;
People smart enough to read & write for this forum ought to know things too.
Queries and some replies about cybernetics were inexcusably but correctably
ignorant. Correction can begin with the review (2 columns) in SCIENCE
257:1146 (1992) of Heims, S. J. THE CYBERNETICS GROUP (MIT Press, 1991). Just
the review; the book is gravy. One of the Max Planck Institutes in Germany is
on "Biological Cybernetics," and there is a scientific journal with that name
in its title. There is a lot more, some of which is in the "What's in a name"
category, people doing cybernetics but not knowing it, or calling what they
were doing cybernetics, only because it sounded good 40 years ago (the Soviet
ploy to escape being tarnished by "psychology" when there was a USSR). I
don't have the exchange in this Digest in front of me, but remember my
astonishment at the naivete displayed on cybernetics "vs" AI. Some smart
people may have forgotten how to read anything but a computer monitor and only
if digital machines feed the crt. The rest of the cure (correction) might
involve exposure to libraries and words in print.
Harry Jerison (ijc1hjj@mvs.oac.ucla.edu - Psychiatry, UCLA)
------------------------------
Subject: Help for signature verification
From: B.NIEVOLA%CEFET.ANPR.BR@UICVM.UIC.EDU
Date: Tue, 31 Aug 93 10:54:00 -0300
Dear Sir,
I'm currently working with neural networks and other AI
applications. One of such is a system for signature verification.
I have one student that is working on another project
and I'd like to obtain information for him. His message is:
"I would like to have some informations (references) about the
applicability of neural networks in the enhancement, limiariza_
tion and segmentation of poor quality images, more specific, in
fingerprint images. Also, information about neural networks in
fingerprint identification would be of great help.
Best regards,
Marcos Lopes"
Can you help him? He has no e-mail, but you can use my
address, to communicate with him. If someone in the list could
give some information, I appreciate. Thank you,
Prof. Julio Cesar Nievola
CEFET-PR
EMAIL: b.nievola@cefet.anpr.br
------------------------------
Subject: neural network society membership
From: rp@rdm.ch (Paulo Rios)
Date: Tue, 31 Aug 93 18:58:06 +0000
Hi!
I would like to join one or two main neural network societies.
Does anyone out there know their e-mail or regular address? Any
information would be welcome.
Thank you.
Paul
==================================================
Paul Rios
KMS Development Lab
Switzerland
E-mail: rp@rdm.ch
==================================================
------------------------------
Subject: neural network research centers
From: rp@rdm.ch (Paulo Rios)
Date: Tue, 31 Aug 93 19:14:08 +0000
Hi!
I am studying the use of neural network techniques in our software
product, a communication network (including cabling) management
system. I am also interested in doing research in some specific
areas of concern to us in the company. Information on research done
elsewhere might prove to be very useful.
Therefore, I would be interested in learning about the major research centers
worldwide (especially in North America, Europe and Australia),
university and industry, in neural network research.
Does anyone out there know of an e-mailing server, paper or book with
a list of these centers plus a brief description of their main areas of
research? What about research in the area I mentioned above?
Any information would be welcome.
Thank you.
Paul
==================================================
Paul Rios
KMS Development Lab
Switzerland
E-mail: rp@rdm.ch
==================================================
------------------------------
End of Neuron Digest [Volume 11 Issue 50]
*****************************************
