Resent: Fri, 09 Sep 88 17:51:34 PDT
Resent: kruschke%cogsci.berkeley.edu@ucbvax.berkeley.edu
Full-Name: Neuron-Digest Moderator Peter Marvit
From: <neuron-request@hplabs.hp.com>
To: Neuron-Distribution
Subject: Neuron Digest V3 #13
Reply-To: Neuron-Request <neuron-request@hplabs.hp.com>
Errors-To: Neuron-Request <neuron-request@hplabs.hp.com>
Organization: Hewlett-Packard Laboratories 
Date: Fri, 15 Jul 88 18:39:44 PDT
Sender: neuron


NEURON Digest	Fri Jul 15 07:21:20 CDT 1988   Volume 3 / Issue 13
Today's Topics:

 a program for dot-pattern for N.N (looking for)
 neural net simulation package
 Theories of Higher Brain Functions via Cerebral Neocortex ?
 Applications of N.Nets
 IEEE San Diego Conference Proceedings
 Grossberg's ART1 code
 Re: IEEE San Diego Conference Proceedings
 Lee Sailer --> Stephen Gallant
 Text recognition
 Rochester Connectionist Simulator -- ANNOUNCEMENTS
 Neural and Brain Modeling  - MacGregor

[[ This starts the backlog of Digests.  I appreciate your patience during
the change.  Keep those cards and letters coming!  Submissions are especially 
welcome. -PM]]

Submissions: neuron@hplabs.hp.com
Requests, policy: neuron-request@hplabs.hp.com
----------------------------------------------------------------------

Date: 6 Jul 88 12:18:24 GMT
From: Fourati Mourad <kddlab!icot32!nttlab!shzkgw!suvax0!fourati@uunet.uu.net>
Subject: a program for dot-pattern for N.N (looking for)
 
 I'm using Neural networks trained with Back propagation algorithm. I need a
program to show on screen the state of the connections weights by dot patterns 
(or square patterns : specifying the weights by blackening squares). If
someone have a general program for that purpose, would you like to email it to
me please.[We have a 4.3 BSD UNIX on VAX and SONY WORKSTATION].
                                              
                                      Thanks in advance
                                      email to Mourad FOURATI
                                      fourati@suvax0.shizuoka.JUNET

------------------------------

Date: 4 Jul 88 04:51:42 GMT
From: killer!tness7!tness1!nuchat!uhnix1!sun1.cs.uh.edu!cristina@ames.arc.nasa.gov
Subject: neural net simulation package
 
I am currently working on general network programming environment for
defining, generating, and modeling of artificial networks.  In 
particular, I'm interested in distributed and parallel implementations
of this kind of systems.  I read some news about the Rochester Simulation
Package and MACIE.  I would be grateful if someone could send me paper
references or contact addresses about research and developments in 
this area.
Thank you.
 
----------
Cristina Ip, U. of Houston Computer Science
Internet: cristina@sun2.cs.uh.edu

------------------------------

Date: Sat, 2 Jul 88 23:44:52 EST
From: munnari!cheops.eecs.unsw.oz.au!ashley@uunet.UU.NET (Ashley M. Aitken)
Subject: Theories of Higher Brain Functions via Cerebral Neocortex ?
 
G'Day !
 
I am presently undertaking to review  theories and models of  the
cerebral  neo-cortex which aim to explain  higher brain functions.
 
To-date I am familiar with the following
 
	Neuronal Group Selection        Edelman, G.
 
	Value Unit Encoding             Ballard, D.
 
	Neocortex Theory                Marr, D.
 
I would be most grateful if anyone knowing of any  references  to
other theories or  models  could  please  e-mail  me the relevant
information. Any leads will be most appreciated.
 
Thanks in Advance, 
sincerely,
Ashley Aitken
 
E-MAIL	:
	ashley@cheops.unsw.oz						ACSnet
	ashley%cheops.unsw.oz@uunet.uu.net				ARPAnet
	ashley@cheops.unsw.oz.au					ARPAnet
	{uunet,ukc,ubc-vision,mcvax}!munnari!cheops.unsw.oz!ashley	UUCP	
	ashley%cheops.unsw.oz@australia					CSnet
	ashley%cheops.unsw.oz@uk.ac.ukc					JAnet
 
POSTAL	:			
	Academic Address:			Residential Address:
	Computer Science Department, EECS,	c/o Basser College,
	University of New South Wales,		The Kensington Colleges,
	Box 1,PO KENSINGTON,N.S.W.,2033,	Box 24,PO KENSINGTON,3033.
	AUSTRALIA.				AUSTRALIA.
	Ph. Aust (02) 697-4055			Ph. Aust (02) 663-8117

------------------------------

Date: 29 Jun 88 11:32:06 GMT
From: Simon Peter Gatrall <sg1q+@ANDREW.CMU.EDU>
Subject: Applications of N.Nets
 
Could someone please send me and/or post some references to some of the gee-wiz
applications of neural-networks.  (I'm writing a paper)
 
-Simon Gatrall                  sg1q+@andrew.cmu.edu

------------------------------

Date: 21 Jun 88 21:02:59 GMT
From: Dan Olson <ssc-vax!dano@BEAVER.CS.WASHINGTON.EDU>
Subject: IEEE San Diego Conference Proceedings
 
I would like to buy the proceedings for this year's conference
in San Diego, but am not planning to attend.  Can anyone tell
me who to contact or how to order?  Hopefully the price won't
be as much as registering for the conference.
 
Thanks,
Dan Olson

------------------------------

Date: 22 Jun 88 17:46:50 GMT
From: David E Demers <beowulf!demers@SDCSVAX.UCSD.EDU>
Subject: Re: IEEE San Diego Conference Proceedings
 
In article <2025@ssc-vax.UUCP> dano@ssc-vax.UUCP (Dan Olson) writes:
>I would like to buy the proceedings for this year's conference
>in San Diego, but am not planning to attend.  Can anyone tell
>me who to contact or how to order?  Hopefully the price won't
>be as much as registering for the conference.
>
>Thanks,
>Dan Olson
 
 
As far as I know, the price has not yet been decided.  Last year's
cost $70 after the fact; this year's proceedings are rumored to be
more, probably about $100.  Two sources:  IEEE publications, which
is your best bet.  I don't have the address handy, check your latest
SPECTRUM.  Also, last year the conference organizers had a few
extras available : contact Nomi Feldman IEEE ICNN 88 conference
secretariat, 3770 Tansy St, San Diego, CA 92121.
 
A third possibility is to find someone who is going & have them get
you a copy.  Proceedings are supposed to be available at the
conference (instead of in December, like last year...).
 
There are a lot of very good papers submitted, these proceedings
should be excellent.
 
Dave DeMers
Department of Computer Science & Engineering
UCSD
(demers@cs.ucsd.edu)

------------------------------

Date: Thu, 23 Jun 88 08:34:15 EDT
From: "Bruce E. Nevin" <bnevin@cch.bbn.com>
Subject: Lee Sailer --> Stephen Gallant
 
For a pointer to Stephen Gallant at Northeastern, I suggest you try
one of the following:
 
	mckee%corwin.css.northeastern.edu@relay.cs.net (George McKee)
	hafner%northeastern.csnet@relay.cs.net (Carole Hafner)
 
(The two paths after the % may be working alternatives for both logins.
I don't know the way from bitnet.)
 
You might also try gallant or sgallant with the above paths to see if
you get through.  Allow for the fact that it is summer and he may
well be away at conferences and the like.


------------------------------

Date: 6 Jul 88 19:19:59 GMT
From: Arun Rao <cs.utexas.edu!milano!pp!cadillac!rao@TUT.CIS.OHIO-STATE.EDU>
Subject: Text recognition
 
This is the first time I'm posting anything on this net, so I was not
able to retrieve the address of the person who wanted to know about 
existing text recognition software using neural nets. 
 
I have a program which implements Grossberg's ART1 (with some modifications) 
for text recognition. It is still rudimentary, but is capable of adaptively
learning to recognize a bit-mapped set of characters at its input. Access after
learning is virtually instantaneous, and the number of characters it can store
depends on how many connections you can simulate in your machine. I have tried
the program with a large number of input nodes and there are no problems. The
time taken by the network to learn (I refer to real time, as in the time taken
if the network were to be built in hardware) does not scale up to any great
degree with the number of nodes (CPU time obviously does).
 
 
Arun Rao
Arizona State University
 
(Currently a summer intern at MCC)
 
-- 
Arun Rao @ MCC VLSI CAD Program [512] 339-3793
P.O. Box 200195, Austin, TX 78720
ARPA: rao@mcc.com
UUCP: {ihnp4,seismo,harvard,gatech,pyramid}!ut-sally!im4u!milano!bell!rao

------------------------------

Date: 12 Jul 88 19:31:51 GMT
From: cs.utexas.edu!milano!pp!cadillac!rao@TUT.CIS.OHIO-STATE.EDU
Subject: Grossberg's ART1 code
 
This is with reference to a posting I made some time ago
regarding a program which simulates Grossberg's ART1 and
uses it to recognize bit-mapped characters.
 
I have received a lot of mail asking me for the source code 
of the program. I appear to have given the impression that I
was intending the program for general distribution.
 
I sincerely regret that I cannot comply with requests for the 
source code at the moment - I will, however, post a message on the
net as soon as I can.
 
In the meantime, I am willing to field any questions (however detailed)
as to methodology and implementation. I spent quite a lot of time
battling through impenetrable prose, and I'm quite willing to share
any insights that I might have gained.
 
Arun Rao
(Post Aug 15th e-mail address: rao%enuxc1.asu.edu@relay.cs.net)

------------------------------

Date: 7 Jul 88 19:00:05 GMT
From: Liudvikas Bukys <rochester!bukys@CU-ARPA.CS.CORNELL.EDU>
Subject: Rochester Connectionist Simulator -- ANNOUNCEMENTS
 
(1)	The Rochester Connectionist Simulator (version 4.1) is now available
	via anonymous FTP from CS.Rochester.EDU.  It is in the public/rcs
	directory.  Read the README file there for more information.
 
	The distribution is too large to mail; the compressed tar file is
	837K bytes, and the uncompressed tar file is 3 Megabytes.
 
	If you have TeX and a PostScript printer, you should be able to produce
	your own copy of the 181-page manual.  If you want a paper copy of the
	manual anyway, send a check for $10 per manual (payable to the
	University of Rochester) to Rose Peet at the above address.
 
	If you are unable to obtain anonymous FTP access to the simulator
	distribution, you can still order a copy the old way.  Contact
		Rose Peet
		Computer Science Department
		University of Rochester
		Rochester, NY  14627
		(USA)
	or <connect@cs.rochester.edu>, and she will send you the 
	approriate forms.
	We are currently charging $150 for a distribution tape and a manual.
	We do not have the facilities for generating invoices, so payment is
	required with any order.
 
(2)	We are setting up electronic mailing lists for use by
	the users of the simulator.  If you have the simulator,
	please sign up!
 
	You can reach other users of the simulator via the users' mailing list:
		<simulator-users@cs.rochester.edu>
	If you are not on this mailing list, and wish to be added, 
	send a note to
		<simulator-request@cs.rochester.edu>
	Please send bug reports to
		<simulator-bugs@cs.rochester.edu>
 
(3)	Official bug patches to date (to be found in the FTP directory):
 
	rcs_v4.1.patch.01	fixes a SERIOUS problem in the logging feature.
	rcs_v4.1.patch.02	fixes some minor syntactic problems in the doc.
 
	The patches can be applied by hand if necessary, but you will
	make your life easier if you obtain the widely-available
	"patch" program, and redirect each patch file into "patch -p".
 
------------------------------

Date: 5 Jul 88 00:20:02 GMT
From: Alan Lee Wendt <wendt@arizona.edu>
Subject: Neural and Brain Modeling  - MacGregor
 
    Good book, if you think that we should model the brains of sea
    slugs before trying to model those of human beans.  It's got
    lots of mud-level neural simulation code in FORTRAN, plus
    an incredible number of references to other work.  The high-level
    connectionist work is less thoroughly covered.  The author is
    at UC Boulder Aerospace Engineering Dept.  (Here, go put this
    brain in the wind-tunnel ...)
 
Alan Wendt

------------------------------

End of NEURON-Digest
********************
