Copy Link
Add to Bookmark
Report
AIList Digest Volume 5 Issue 269
AIList Digest Monday, 16 Nov 1987 Volume 5 : Issue 269
Today's Topics:
Neuromorphics - Inference,
Methodology - Animal Behavior and AI & Traditional Techniques,
Bibliography - Object-Oriented Databases
----------------------------------------------------------------------
Date: Sun, 15 Nov 87 11:53:10 EST
From: Brady@UDEL.EDU
Subject: bpsim code
I am interested in inferring concepts from data, and have
been reading about back propagation in neural nets as a
way to make such inferences.
I am confused about the little red riding hood article in BYTE.
The article seems to suggest that the nodes in the middle layer
(representing the concepts wolf, granny, woodcutter)
are INFERRED during training. Other literature on back propagation
that I have seen also suggest that concepts can be inferred
that way. But a look at the BPSIM code that implements the little red
riding hood network seems to suggest the existance of these three nodes
before training begins. So my question is: if one wants to infer
concepts from data, can one do that by using back propagation?
Or do you still have to a priori anticipate the existance of the
concepts?
[I haven't seen the example in question, but the usual neural network
learning procedure does use predefined nodes. The nodes of the center
layer are identical except for random variations in the initial
weights. After training, these nodes take on very different roles
characterized by their weight vectors. Determining what these roles
are can be quite difficult, so it is not clear how much of the inference
is done by the network and how much by the human -- but clearly the
network has done part of the work. This strategy permits nodes to be
deleted (via zeroed weights), but not created. For creation of nodes
you may have to investigate genetic learning algorithms. -- KIL]
------------------------------
Date: 13 Nov 87 23:30:58 GMT
From: Michael P. Smith <mps@cs.duke.edu>
Reply-to: mps@duke.UUCP (Michael P. Smith)
Subject: Re: animal behavior and AI
Article-I.D.: duke.10631
In article <8711110303.AA28544@ADS.ARPA> dan@ADS.ARPA (Dan Shapiro) writes:
> ... My goal is to develop a realistic view of what
>planning means to simple animals (at the level of ants for example)
>and use that information to motivate planning architectures within AI.
>Within this context, my focal point is to look at *errors* in animal
>behavior, as when ants build circular bridges out of their own bodies,
>and the ones on top simply run themselves to death.
Hofstadter calls such revealing lapses of animal cunning "sphexishness"
after a famous example from Wooldridge. Chapter 2 of Dennett provides
more philosophical analysis of the phenomenon.
Dennett, Daniel C. _Elbow Room_, MIT 1984.
Hofstadter, Douglas. "On the Seeming Paradox of Mechanizing
Creativity," _Scientific American_ (September 1982), reprinted as
chapter 23 of _Metamagical Themas_, Basic Books, 1985.
Wooldridge, Dean. _The Machinery of the Brain_, McGraw Hill, 1963.
----------------------------------------------------------------------------
Michael P. Smith mps@cs.duke.edu / {seismo,decvax}!mcnc!duke!mps
"V. That which a lover takes against the will of his beloved has no relish."
Andreas Capellanus' "Rules of Love" from _The Art of Courtly Love_
------------------------------
Date: 9 Nov 87 01:53:52 GMT
From: clyde!burl!codas!killer!usl!usl-pc!jpdres10@rutgers.edu (Green
Eric Lee)
Subject: Re: Practical effects of AI (speech)
In message <267@PT.CS.CMU.EDU>, kfl@SPEECH2.CS.CMU.EDU (Kai-Fu Lee) says:
>In article <12@gollum.Columbia.NCR.COM>, rolandi@gollum.Columbia.NCR.COM
(rolandi) writes:
>> It would seem to me that the single greatest practical advancement for
>> AI will be in speaker independent, continuous speech recognition. This
>(3) If this product were to materialize, it is far from clear that it
> would be an advancement for AI. At present, the most promising
> techniques are based on stochastic modeling, pattern recognition,
> information theory, signal processing, auditory modeling, etc..
> So far, very few traditional AI techniques are used in, or work well
> for speech recognition.
Very few traditional AI techniques have resulted in much at all :-)
(sorry, I couldn't help it).
But seriously, considering that sciences such as physics and
mathematics have been ongoing for centuries, can we REALLY say that AI
has "traditional techniques"? Certainly there is a large library of
techniques available to AI researchers today, but 30 years is hardly
a long enough time to call something "traditional". Remembering how
going beyond the "traditional" resulted in many breakthroughs in
mathematics and physics, saying that "it is far from clear that it
would be an advancement for AI" presupposes that one defines AI as
"that science which uses certain traditional methods", which, I
submit, is false.
--
Eric Green elg@usl.CSNET from BEYOND nowhere:
{ihnp4,cbosgd}!killer!elg, P.O. Box 92191, Lafayette, LA 70509
{ut-sally,killer}!usl!elg "there's someone in my head, but it's not me..."
------------------------------
Date: 14 Nov 87 17:43:45 GMT
From: nosc!humu!uhccux!lee@sdcsvax.ucsd.edu (Greg Lee)
Subject: Re: Practical effects of AI (speech)
In article <244@usl-pc.UUCP> jpdres10@usl-pc.UUCP (Green Eric Lee) writes:
>In message <267@PT.CS.CMU.EDU>, kfl@SPEECH2.CS.CMU.EDU (Kai-Fu Lee) says:
>>In article <12@gollum.Columbia.NCR.COM>, rolandi@gollum.Columbia.NCR.COM
(rolandi) writes:
>>> It would seem to me that the single greatest practical advancement for
>>> ...
>> So far, very few traditional AI techniques are used in, or work well
>> for speech recognition.
>
>Very few traditional AI techniques have resulted in much at all :-)
I suppose that applying AI to speech recognition would involve
making use of what we know about the perceptual and cognitive nature
of language sound-structures -- i.e. the results of phonology. I don't
know that this has ever been tried. If it has, could someone supply
references? I'd be very interested to know what has been done in this
direction.
Greg Lee, lee@uhccux.uhcc.hawaii.edu
------------------------------
Date: 13 Nov 87 22:11:40 GMT
From: clyde!burl!codas!killer!pollux!ti-csl!!peterson@rutgers.edu
(Bob Peterson)
Subject: Re: object oriented database query
In article <4528@cc5.bbn.COM> mfidelma@bbn.COM (Miles Fidelman) writes:
>Can anyone point me to work in the area of applying database technology
>to supporting object oriented environments?
Sure. See the short bibliography attached to the end of this message.
It is about two pages in length. Several publications are of special
interest: Proceedings of OOPSLA '86 and '87, and the Proceedings of the
OODB Workshop held in '86 in Pacific Grove, CA. In each of these you'll
find interesting articles addressing OODB issues, as well as many
additional references following each article.
>It strikes me that database technology tends to focus on supporting large
>production databases, with attention to fast processing speeds, maintaining
>database integrity, journalizing/checkpointing, etc.; while object oriented
>environments are basically prototyping environments.
I don't believe OODB's are, as you put it, "...basically prototyping
environments." Indeed, there are applications, such as VLSI CAD and
hypertext, that are not well-supported by conventional databases.
When implemented using an object-oriented style, these applications
use many objects with rather complex and dynamic interconnections.
Conventional data models, i.e., hierarchical, network, and relational,
don't handle the complex, dynamic interconnected objects very well.
At least that's my opinion.
>Has anyone been working on making a production object oriented environment?
Yes, we at Texas Instruments are working on just such an effort. In
addition there are at least three companies now offering for sale
object-oriented database systems.
Hardcopy and Electronic Addresses:
Bob Peterson Compuserve: 76703,532
P.O. Box 1686 Usenet: peterson@csc.ti.com
Plano, Tx USA 75074 (214) 995-6080
(Skip the rest of this message if you aren't interested in two pages
of bibliographic references.)
OBJECT-ORIENTED DATABASE SYSTEMS BIBLIOGRAPHY
[BCG*87]J. Bannerjee, H.T. Chou, J.F. Garza, W. Kim, D.
Woelk, N. Ballou, and H.J. Kim. Data Model Issues For
Object-Oriented Applications. ACM Transactions on Office
Information Systems, January 1987.
[BD81] A. J. Baroody and D. J. DeWitt. An Object-
Oriented Approach to Database System Implementation.
ACM Transactions on Database Systems, 6(4):576-601,
December 1981.
[bFL85] Edited by F. Lochovsky. IEEE Database Engineering.
December 1985. A quarterly bulletin of the IEEE Computer
Society Technical Committee on Database Engineering,
Special Issue on Object-Oriented Systems.
[But86] M. H. Butler. An Approach to Persistent LISP Objects. In
Proc. COMPCON, pages 324-329, IEEE, San Fransisco, CA,
March 1986.
[CAC*84]W. Cockshott, M. Atkinson, K. Chisholm, P. Bailey,
and R. Morrison. Persistent Object Management System.
Software Practice and Experience, 14:49-71, 1984.
[Mis84] N. Mishkin. Managing Permanent Objects. Technical
Report YALEU/DCS/RR-338, Department of Computer Science,
Yale University, New Haven, CT, November 1984.
[ML87] T. Merrow and J. Laursen. A Pragmatic System for Shared
Persistent Objects. In N. Meyrowitz, editor, OOPSLA '87
Conference Proceedings, pages 103-110, ACM, ACM, New
York, NY, Oct 4-8 1987.
[Nie85] O. M. Nierstrasz. Hybrid: A Unified Object-Oriented
System. IEEE Database Engineering, 8(4):49-57, December
1985.
[OBS86] P. O'Brien, B. Bullis, and C. Schaffert. Persistent
and Shared Objects in Trellis/Owl. In Proceedings
of the 1986 International Workshop on Object-Oriented
Database Systems, pages 113-123, ACM, Pacific Grove,
CA, September 1986.
[OOD86] Proceedings of the International Workshop on Object
Oriented Database Systems, Pacific Grove, CA, September
1986. ACM.
[OOP86] ACM. Conference Proceedings for the Object-Oriented
Programming Systems, Languages and Applications '86
Conference (OOPSLA '86), Portland, OR, Sept 29-Oct 2 1986
Panel Discussion.
[Pet87] R. W. Peterson. Object-Oriented Database Design. AI
Expert, 2(3):27-31, March 1987.
[SR86] M. Stonebraker and L. Rowe. The Design of POSTGRES. In
Proceedings of SIGMOD, pages 340-355, Washington D.C.,
December 1986.
[SZ86] A. Skarra and S. Zdonik. The Management of Changing
Types in an Object-Oriented Database. In Norman
Meyrowitz, editor, OOPSLA '86 Conference Proceedings,
pages 483-495, ACM, ACM, Portland, OR, September 1986.
[SZ87] K. Smith and S.B. Zdonik. Intermedia: A Case Study of
the Differences Between Relational and Object-Oriented
Database Systems. In N. Meyrowitz, editor, OOPSLA '87
Conference Proceedings, pages 452-465, ACM, ACM, New
York, NY, Oct 4-8 1987.
[SZR86] A. S. Skarra, S. Zdonik, and S. Reiss. An Object
Server for an Object Oriented Database System. In
International Workshop on Object Oriented Database
Systems, pages 196-205, Pacific Grove, CA, September
1986.
[Tho86] C. Thompson. Object-oriented databases. Texas In-
struments Engineering Journal, 3(1):169-175, Jan. 1986.
[TMT86] C.W. Thompson, S. Martin, and S. Thatte. Real-Time
Object-Oriented Manufacturing Databases. In AAAI 1986
Workshop on AI in Manufacturing, Aug 1986.
[Wie86] G. Wiederhold. Views, Objects, and Databases. IEEE
Computer, ():37-44, December 1986.
Hardcopy and Electronic Addresses: Office:
Bob Peterson Compuserve: 76703,532 NB 2nd Floor CSC Aisle C3
P.O. Box 1686 Usenet: peterson@csc.ti.com
Plano, Tx USA 75074 (214) 995-6080 (work) or (214) 596-3720 (ans. machine)
------------------------------
End of AIList Digest
********************
