Copy Link
Add to Bookmark
Report
AIList Digest Volume 5 Issue 221
AIList Digest Tuesday, 29 Sep 1987 Volume 5 : Issue 221
Today's Topics:
Queries - Unification Benchmarks & Real-Time AI in Italy &
Reading List & J.F. Allen's Work on Time & Boltzmann Machine &
Vivarium Project & AAAI Speeches,
Neural Networks - ASSP Reference & Hinton's Recirculation Algorithm,
Comments - Goal of AI: Where Are We Going?
----------------------------------------------------------------------
Date: 22 Sep 87 14:12:12 GMT
From: unc!bts@mcnc.org (Bruce Smith)
Subject: Unification benchmarks?
Does anyone have a good set of unification problems? I want to run
simulations of unifications on an architecture being developed here
at UNC, and I'd like a set of "typical" problems. (And, I guess I'd
also like to be able to say I'm not the only one who claims they're
typical.)
A paper by Trum and Winterstein, referenced by Martelli & Montanari,
might have what I'm looking for. Can anyone supply a copy of
Trum P. and Winterstein,G. "Description, implementation and
practical comparison of unification algorithms," Internal Rep.
6/78, Fachbereich Informatik, Univ. of Kaiserlautern, Germany.
Other references on this topic are welcome, also. Thanks!
__________________________________
Bruce T. Smith, bts@unc.cs.unc.edu
Dept. of Computer Science
Sitterson Hall/ UNC-CH
Chapel Hill, NC 27514
------------------------------
Date: Thu, 24 Sep 87 09:42:10 edt
From: WRM%WPI.BITNET@wiscvm.wisc.edu
Subject: Looking for researchers
I have a colleague who is looking for current AI
research activity in Italy. In particular he is
interested in real-time AI systems. Does anyone
know of such activity? Thanks in advance.
Bill Michalson Bitnet wrm@wpi
Arpanet wrm%wpi.BITNET@wiscvm.ARPA
------------------------------
Date: 23 Sep 87 17:42:39 GMT
From: ihnp4!chinet!nucsrl!ragerj@ucbvax.Berkeley.EDU (John Rager)
Subject: Paper Request
I am going to teach a course called Applied AI. The student are generally
upperclass and graduate students in engineering fields (but not in
computer science). I am trying to gather a reading list for the course.
I would like suggestions for papers about applications in engineering,
manufacturing, management, etc. The papers should:
1. be well written
2. be about an attack on a (quasi-)real problem
3. be detailed enough to convey understanding of what was done
and how it was done (technical reports are fine).
Please send suggestions and I will summarize later.
Thank-you
John Rager
------------------------------
Date: 24 Sep 87 09:14:00 GMT
From: mcvax!unido!uklirb!noekel@uunet.uu.net
Subject: J.F.Allen's work on time - (nf)
Hi there,
in Communications of the ACM of November 1983 James F. Allen describes
several extensions to his well-known temporal logic, such as reference
intervals, a duration reasoner, and a date-line feature. I would like to know
if any of these extensions have actually been implemented and tested. Are
there subsequent papers on this line of research that I have missed? Ditto
for papers containing critical remarks by other people? Perhaps James Allen
is on the net himself?!?
Happy inferring
Klaus Noekel
Universitaet Kaiserslautern
Fachbereich Informatik
P.O.Box 3049
6750 Kaiserslautern
West Germany
UUCP: ...!mcvax!unido!uklirb!noekel
"Why should I worry about opinions? I'll stick to my prejudices!"
------------------------------
Date: Sun, 27 Sep 87 15:25:30 EDT
From: Ali Minai <amres%uvaee.ee.virginia.edu@RELAY.CS.NET>
Subject: Boltzmann Machine
While reading two different references about the Boltzmann Machine, I came
across something I did not quite understand. I am sure that there is a
perfectly reasonable explanation, and would be glad if someone could point
it out.
In chapter 7 of PARALLEL DISTRIBUTED PROCESSING (Vol 1), by Hinton and
Sejnowski, the authors define Pij+ as the probability of units i and j
being on when ALL visible units are being clamped, and Pij- as the
probability of i and j being on when NONE of the visible units are
being clamped (pp 294, 296). They then proceed to present the expression
for the gradient of G with respect to weights Wij as -1/T (Pij+ - Pij-).
However, in the paper entitled LEARNING SYMMETRY GROUPS WITH HIDDEN
UNITS: BEYOND THE PERCEPTRON, by Sejnowski, Keinker and Hinton, in
Physica 22D (1986), pp 260-275, it is explicitly stated that Pij+
is the probability when ALL visible units (input and output) are being
clamped, BUT Pij- is the probability of i and j being on when ONLY THE
INPUT UNITS ARE CLAMPED (pp 264). So there seems to be no concept of
FREE-RUNNING here.
Since the expression for dG/dWij is the same in both cases, the
definitions of Pij- must be equivalent. The only explanation I could
think of was that "clamping" the inputs ONLY was the same thing as letting
the environment have a free run of them, so the case being described is
the free-running one. If that is true, obviously there is no contradiction,
but the terminology sure is confusing. If that is not the case, will
someone please explain.
Also, can anyone point out any latest references to work on the Boltzmann
Machine?
Thanks,
Ali.
---------------------------------------------------------------------------
Ali Minai,
Department of Electrical Engg.
University of Virginia,
Charlottesville, Va 22901.
ARPANET: amres@uvaee.ee.Virginia.EDU
------------------------------
Date: Mon, 28 Sep 87 07:07:25 PDT
From: erickson@lbl-csam.arpa (Marvin Erickson [ams-pnl])
Subject: Vivarium Project
Does anyone know the status of Alan Kay's Vivarium Project? (Rumored or
officially published?) If Apple isn't giving out any info, how about the
MIT Media Lab? I've only hear a little in MacWeek articles and the like.
Also, MacWeek mentioned a related program called "BrainWorks" -- any MIT-ers
willing to offer a more detailed description than what the mag gave?
Mark A. Whiting
(c/o erickson@lbl-csam)
------------------------------
Date: Fri, 25 Sep 87 13:13:22 PDT
From: AAAI <AAAI-OFFICE@SUMEX-AIM.STANFORD.EDU>
Subject: help!
If anyone has made a tape of Pat Winston's Presidential Address from AAAI-87,
the AAAI would really appreciate a copy. Our copy got scrappled.
Two other AAAI Presidents, Marvin Minsky and Ed Feigenbaum, would also like
audio tapes of their Presidential Addresses if anyone has them.
Thanks,
Claudia Mazzetti
AAAI
445 Burgess Drive
Menlo Park, CA 94025
------------------------------
Date: 24 Sep 87 17:49:54 GMT
From: ur-tut!mkh1@cs.rochester.edu (Manoj Khare)
Subject: Re: Neural Networks & Unaligned fields
In article <1241@uccba.UUCP> finegan@uccba.UUCP (Mike Finegan) writes:
>In article <759@ucdavis.UUCP>, g451252772ea@ucdavis.UUCP (g451252772ea) writes:
>> > IEEE ASSP (Acoustics, Speech, and Signal Processing) April 1987,
>>
>> I found the 4/87 issue (and the rest of 1987) , but not this article.
>> Are you certain of this reference? Thanks...
>>
>I am not sure if it was April (I believe it was), but the whole journal is
>devoted to the subject of Neural Nets for that issue, and definitely exists.
> - Mike Finegan
> ...!{hal|pyramid}!uccba!finegan
The article "An Introduction to Computing with Neural Nets" by Richard P.
Lippmann appeared in IEEE ASSP magazine april 1987, pp 4-22.
Q. Does anybody have any idea if the book "Analog VLSI and Neural Systems" by
Carver A. Mead is published yet? OR Is there any way I could get his lecture
notes on the related course at CalTech? Thanks in advance.
..... Manoj Khare
------------------------------
Date: 27 Sep 87 06:43:56 GMT
From: deneb.ucdavis.edu!g451252772ea@ucdavis.ucdavis.edu
(0040;0000009606;0;327;142;)
Subject: references: IEEE ASSP and Hinton's recirculation algorithm
Thanks for the help with the IEEE ASSP reference; indeed I was looking
at the journal, not the 'magazine' (two shelves up, higher than me). It
appears worth the second trip.
Now: Geoffrey Hinton claims to have a new 'recirculation' algorith for
back-propagation, which is claimed to be 'more biologically realistic'
according to the Nature commentary reporting his claim (Nature, 7/9/87,
p. 107) (That's July, not Sept, for all you over-sea folk). But only
that commentary has appeared- I don't know where (if) Hinton has published
the algorithm itself. The commentary only mentions 'a packed audience at
the Society of Experimental Psychology', not even stating where the meeting
was.
Any ideas?
Thanks - Ron Goldthwaite, Psychology & Animal Behavior, U.Cal. Davis
'Economics is a branch of ethics pretending to be a science;
Ethology is a science, pretending relevance to ethics'
------------------------------
Date: 25 Sep 87 04:19:19 GMT
From: cbosgd!osu-cis!tut!dlee@ucbvax.Berkeley.EDU (Dik Lee)
Subject: Re: Neural Networks & Unaligned fields
In article <1241@uccba.UUCP> finegan@uccba.UUCP (Mike Finegan) writes:
>In article <759@ucdavis.UUCP>, g451252772ea@ucdavis.UUCP (g451252772ea) writes:
>> > IEEE ASSP (Acoustics, Speech, and Signal Processing) April 1987,
>>
>> I found the 4/87 issue (and the rest of 1987) , but not this article.
>> Are you certain of this reference? Thanks...
>>
>I am not sure if it was April (I believe it was), but the whole journal is
>devoted to the subject of Neural Nets for that issue, and definitely exists.
Yes, the paper appeared in IEEE ASSP magazine, Apr. 1987. Be sure you are
looking at ASSP magazine, not Journal of ASSP; they are two different
publications.
- Dik Lee Dept. CIS, Ohio State Univ.
------------------------------
Date: 25 Sep 87 10:04:22 GMT
From: ihnp4!homxb!mtuxo!mtune!codas!killer!usl!khl@ucbvax.Berkeley.EDU
(Calvin K. H. Leung)
Subject: Goal of AI: where are we going?
Should the ultimate goal of AI be the perfecting of human intel-
ligence, or the imitating of intelligence in human behavior?
We all admit that the human mind is not flawless. Bias decisions
can be made due to emotional problems, for instance. So there is
no point trying to imitate the human thinking process. Some
current research areas (neural networks, for example) use the
brain as the basic model. Should we also spend some time on the
investigation of some other models which could be more efficient
and reliable?
Provided that we have the necessary technology to build robots
that are highly intelligent; they are efficient and reliable and
they do not possess any "bad" characteristic that man has. Then
what will be the roles man plays in the society where his intel-
ligence can be viewed as comparatively "lower form"?
AI, where are we going?
------------------------------
Date: 27 Sep 87 17:47:22 GMT
From: su-russell!nakashim@labrea.stanford.edu (Hideyuki Nakashima)
Subject: Re: Goal of AI: where are we going?
In article <178@usl> khl@usl.usl.edu.UUCP (Calvin Kee-Hong Leung) writes:
>
>We all admit that the human mind is not flawless. Bias decisions
>can be made due to emotional problems, for instance. So there is
>no point trying to imitate the human thinking process.
I believe that those "bad" characteristics of human are necessary
evils to intelligence. For example, although we still don't understand
the function of emotion in human mind, a psychologist Toda saids that
it is a device for servival. When an urgent danger is approaching, you
don't have much time to think. You must PANIC! Emotion is a meta-
inference device to control your inference mode (mainly of recources).
If we ever make a really intelligent machine, I bet the machine
also has the "bad" characteristics. In summary, we have to study
why human has those characteristics to understand the mechanism of
intelligence.
Hideyuki Nakashima
nakashima@csli.stanford.edu
(or nakashima%etl.jp@relay.cs.net)
------------------------------
End of AIList Digest
********************