Copy Link
Add to Bookmark
Report
AIList Digest Volume 5 Issue 007
AIList Digest Monday, 19 Jan 1987 Volume 5 : Issue 7
Today's Topics:
Queries - Character Recognition & Lisp Machine Window Systems &
Scheme & TOOLKIT,
Games - Go,
Sources - Postings from AI EXPERT Magazine,
Magazine - Canadian Artificial Intelligence,
Report - Learning to Predict
----------------------------------------------------------------------
Date: 13 Jan 87 13:30:41 GMT
From: lerouf.dec.com!denis@decwrl.dec.com (MICHEL DENIS, @KALAMAZOO@VBO)
Subject: Character recognition.
About CHARACTER RECOGNITION :
Has anybody a list of books and publications related to character/words
recognition and its algorithms ? Also especially any piece of software which
implements some of those techniques would be useful for a start !
Thanks in advance and regards,
Michel.
ps: please mail me on :
(DEC E-NET) LEROUF::DENIS
(UUCP) ...decvax!decwrl!dec-rhea!dec-lerouf!denis
(ARPA) denis%lerouf.DEC@decwrl.ARPA
[For a starter, try Srihari's IEEE tutorial on Computer Text Recognition
and Error Correction. The annual conferences on Pattern Recogniton are
good, and there are always some papers on character recognition in the
annual conferences on Computer Vision and Pattern Recognition (formerly
Pattern Recognition and Image Processing). -- KIL]
------------------------------
Date: Thu, 15 Jan 87 09:58:16 PST
From: TAYLOR%PLU@ames-io.ARPA
Subject: Request for Info on Lisp Machine Window Systems
We have been developing a user interface for a planning/scheduling
application on the Symbolics, using Version 6.1 windows and flavors.
For future long term development of the user interface, we are
considering a possible change of the window system, before converting
to Genera 7.0 Dynamic windows and Presentation types. We have heard
mention of XWINDOWS and are interested in knowing about it and other
"generic" window systems and the trade-offs between specialized
features and portability.
Issues we are looking at:
o will window system be compatible with a future Common
lisp window standard
o will window system be portable between lisp machines and
AI work stations, e.g. Symbolics, TI, LMI, Xerox, Sun, ..
o how much conversion will be required to go from current
implementation, now running under Genera 7.0, to a new
window system
o what are advantages/disadvantages of potential window
systems as far as ease of implementation, facilities
available to present information to user, use of object
oriented techniques, etc
o availability of potential window systems on the Symbolics
Opinions and recommendations are solicited from Lisp machine users
as to their experience and preferences. Please respond by e-mail.
I will summarize for this bboard if requested and sufficient responses
are received.
Thanks - Will
Will Taylor - Sterling Software, MS 244-7,
NASA-Ames Research Center, Moffett Field, CA 94035
arpanet: taylor%plu@ames-io.ARPA
uusenet: ..!ames!pluto.decnet!taylor
phone : (415)694-6525
------------------------------
Date: 15 Jan 87 19:42:44 GMT
From: crawford@husc4.harvard.edu (alexander crawford)
Subject: Re: IEEE Computer Society Meeting on AI Workstation (in Denver)
In article <729@druxv.UUCP> sandy@druxv.UUCP (BishSL) talks about
getting a copy of text on the SCHEME language. Does anyone know if
this is available on PC's yet?
---Alec Crawford
------------------------------
Date: Sat, 17 Jan 87 12:55 EST
From: Hoebel@RADC-MULTICS.ARPA
Subject: TOOLKIT
Anyone who has used Richard Cullingford's TOOLKIT and would
like to share experiences/knowledge with our natural language group at
Rome Air Development Center, please contact Walter at RADC-TOPS20 or
Hoebel at RADC-MULTICS.
------------------------------
Date: 15 Jan 87
From: vnend@ukecc.uky.csnet (D. W. James)
Reply-to: vnend@ukecc.UUCP (D. W. James)
Subject: Re: Go
Forwarded by: <cbosgd!ecc.engr.uky.csnet!edward@seismo.CSS.GOV>
"Edward C. Bennett" <ukecc!edward@seismo.CSS.GOV>
In article <8701120553.AA08679@ucbvax.Berkeley.EDU> 900380@UMDD.BITNET
(Troy Shinbrot) writes:
>Rumor has it that programs which play Go on personal computers have recently
>become available.
>- Troy Shinbrot (aka. 900380@umdd.bitnet)
The one encounter that I have had with a GO program was very
disappointing. The program is titled simply "Go" and is from Hayden
Software (Sargon III, among others). I am not an experianced player,
less than 50 games vs human opponents and a little reading, and I had
no problem beating it even with a 9 stone handicap.
Later y'all, Vnend Ignorance is the Mother of Adventure.
UUCP:cbosgd!ukma!ukecc!vnend; or vnend@engr.uky.csnet; or cn0001dj@ukcc.BITNET
------------------------------
Date: 14 Jan 87 23:30:08 GMT
From: imagen!turner@ucbvax.Berkeley.EDU (D'arc Angel)
Subject: source postings from AI EXPERT magazine
The following was posted to mod.sources, but that group seems to be
somewhat back logged.
I have the following sources from AI EXPERT magazine and will post
them if there is enough interest, my intention is to do this on a
monthly basis and i need feedback as to:
a) is this desired
b) should i just post the index and post the sources (in arc format)
only if there is interest
c) should i post the sources every month and assume there is enough
interest to justify the network traffic
and now for this month's list of software, for now send me email if
you want the sources and if i get enough requests i will post the
whole arc file.
=======+=======+=======+=======+=======+=======+=======+=======+=======+=====
Articles and Departments that have
Additional On-Line Files
AI EXPERT
January 1987
(Note: Contents page is in file CONTNT.JAN)
ARTICLES RELEVANT FILES
January Table of Contents CONTNT.JAN
Adding Rete Net to Your OPS5 Toolbox OPSNET.JAN
by Dan Neiman
Perceptrons & Neural Nets PERCEP.JAN
by Peter Reece
DEPARTMENTS
Expert's Toolbox EXPERT.JAN
"Using Smalltalk to Implement Frames"
by Marc Rettig
AI Apprentice AIAPP.JAN
"Creating Expert Systems from Examples"
by Beverly and Bill Thompson
C'est la vie, C'est la guerre, C'est la pomme de terre
Mail: Imagen Corp. 2650 San Tomas Expressway Santa Clara, CA 95052-8101
UUCP: ...{decvax,ucbvax}!decwrl!imagen!turner AT&T: (408) 986-9400
------------------------------
Date: Tue, 13 Jan 87 17:56:49 est
From: Graeme Hirst <gh%ai.toronto.edu@RELAY.CS.NET>
Subject: /Canadian Artificial Intelligence/ magazine
The January 1987 issue of /Canadian Artificial Intelligence/ has just been
mailed, and all members of CSCSI/SCEIO should be receiving it soon (Canada
Post willing).
/Canadian A.I./ is a quarterly magazine sent to all members of CSCSI/SCEIO,
the Canadian artificial intelligence society. The society, founded in 1973,
has over 1000 members, and sponsors the bienniel Canadian A.I. conference as
well as the magazine. (The next conference is in Edmonton, May 1988.)
If you aren't a member and would like to be (and everyone working in A.I. in
Canada should be!), then send $25* (students $15*) to:
CSCSI/SCEIO, c/o CIPS
243 College Street, 5th floor
Toronto, Ont
CANADA M5T 2Y1
Ask for your membership to start with the January 1987 issue.
No, you don't have to be a Canadian to be a member. Anyone who wants to know
what's going on in A.I. in Canada is welcome!
*Prices are in Canadian dollars; U.S. funds accepted at current exchange rates:
full membership, US$18.50; student membership US$11.25.
Graeme Hirst
Senior Editor
------------------------------
Date: Fri, 16 Jan 87 17:24:25 EST
From: Rich Sutton <rich%gte-labs.csnet@RELAY.CS.NET>
Subject: TR Abstract -- Learning to Predict
------------------------------------------------------------------------
LEARNING TO PREDICT
BY THE METHODS OF TEMPORAL DIFFERENCES
Richard S. Sutton
GTE Labs
Waltham, MA 02254
Rich@GTE-Labs.CSNet
This technical report introduces and provides the first formal results
in the theory of TEMPORAL-DIFFERENCE METHODS, a class of statistical
learning procedures specialized for prediction---that is, for using past
experience with an incompletely known system to predict its future
behavior. Whereas in conventional prediction-learning methods the error
term is the difference between predicted and actual outcomes, in
temporal-difference methods it is the difference between temporally
successive predictions. Although temporal-difference methods have been
used in Samuel's checker-player, Holland's Bucket Brigade, and the
author's Adaptive Heuristic Critic, they have remained poorly
understood. Here we prove the convergence and optimality of
temporal-difference methods for special cases, and relate them to
supervised-learning procedures. For most real-world prediction
problems, temporal-difference methods require less memory and peak
computation than conventional methods AND produce more accurate
predictions. It is argued that most problems to which supervised
learning is currently applied are really prediction problems of the sort
to which temporal-difference methods can be applied to advantage.
--------------------------------------------------------------------------
p.s. Those who have previously requested a paper on "bootstrap learning"
are already on my mailing list and should receive the paper sometime next week.
------------------------------
End of AIList Digest
********************
