Copy Link
Add to Bookmark
Report

AIList Digest Volume 4 Issue 059

eZine's profile picture
Published in 
AIList Digest
 · 1 year ago

AIList Digest           Wednesday, 19 Mar 1986     Volume 4 : Issue 59 

Today's Topics:
Seminars - Learning Symbolic Object Models from Images (MIT) &
Exploration, Search, and Discovery (Rutgers) &
Learning Arguments of Functional Descriptions (Rutgers),
Seminar Series - AI in Design and Manufacturing (SU),
Conference - Object Oriented Database Systems &
US Army (ARO) AI Workshop

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

Date: Mon, 17 Mar 1986 22:44 EST
From: JHC%OZ.AI.MIT.EDU@XX.LCS.MIT.EDU
Subject: Seminar - Learning Symbolic Object Models from Images (MIT)

[Forwarded from the MIT bboard by SAWS@MC.LCS.MIT.EDU.]


Thursday , March 20 4:00pm Room: NE43- 8th floor Playroom

The Artificial Intelligence Lab
Revolving Seminar Series


LEARNING SYMBOLIC OBJECT MODELS FROM IMAGES

Jonathan Connell

AI Lab, MIT

This talk will present the results of an implemented system for
learning structural prototypes of objects directly from gray-scale
images. The vision component of this system employs Brady's Smoothed
Local Symmetries to divide an object into parts which are then
described symbolically. The learning component takes these
descriptions and forms a model of the examples presented in a manner
similar to Winston's ANALOGY program. The problem of matching complex
structured descriptions and the difficult task of reasoning about
function from form will also be briefly discussed.


Refreshments at 3:30

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

Date: 14 Mar 86 14:34:24 EST
From: PRASAD@RED.RUTGERS.EDU
Subject: Seminar - Exploration, Search, and Discovery (Rutgers)

Exploration, Search and Discovery

By:
Michael Sims (MSims@Rutgers.Arpa)
Departments of Mathematics and Computer Science
Rutgers University

March 18, 1986, Tuesday, 11 AM
Hill Center #423

Search has shown immense utility as a theoretical description of what
our computer programs do. We would like to apply the same descriptive
methods to describing discovery systems, such as Eurisko, Bacon, or
the speaker's IL (named for Imre Lakatos) system. Some investigations
by discovery systems are of a sufficiently distinct character, that it
has proved useful to create a new classification for them, called
Exploration.

To form the appropriate distinctions we begin by giving a definition of
what Newell and Simon called Physical Symbol Systems in their Turing
Award Lecture. We then describe two subclasses of Physical Symbol
Systems: 'Search' and 'Exploration'. Search roughly corresponds to what
is most frequently meant by the term, and contains an explicit test for
a solution structure. Exploration on the other hand has no explicit
termination condition, and hence does not value the elements of the
exploration space in terms of a solution structure.

Discovery may be done by either exploration or search. Eurisko and IL
do exploration at the top level, although many of their subtasks are
accomplished via searches. On the other hand, Bacon and IL-BP, an
explanation based learning component of IL, do discovery by doing
search.

Although many problems can be implemented as either search or
exploration, some problem are more naturally, or efficiently
implemented as one or the other. This new classification leads to an
evaluation of the relative efficiencies, the appropriateness
of introducing randomness, and the different roles played by the
search and the exploration evaluation functions.

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

Date: 18 Mar 86 13:06:15 EST
From: PRASAD@RED.RUTGERS.EDU
Subject: Seminar - Learning Arguments of Functional Descriptions (Rutgers)

Machine Learning Colloquium


LEARNING ARGUMENTS OF INVARIANT FUNCTIONAL DESCRIPTIONS

Mieczyslaw M. Kokar
Northeastern University
360 Huntington Avenue
Boston, MA 02115

11 AM, March 25, Tuesday
#423, Hill Center


The main subject of this presentation is discovery of concepts from
observation. The focus is on a special kind of concepts - arguments of
functional descriptions. The functions considered here are to be
meaningful, i.e., computable functions expressed in terms of the operations
defining the representation language in which the concepts are described.
Such functions are invariant under transformations of the representation
language into equivalent representations.

It will be shown that the feature of invariance can be utilized in
formulating and testing hypotheses about relevance of arguments of functional
descriptions. The main point is that the arguments do not need to be changed
to test the relevance. This is very important to the discovery process as the
arguments to be discovered are not known, therefore, how could they be
controlled?

Simple examples of discovering concepts of physical parameters (arguments
of physical laws) will be discussed.

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

Date: Tue 18 Mar 86 12:44:05-PST
From: Marty Tenenbaum <Tenenbaum@SRI-KL>
Subject: Seminar Series - AI in Design and Manufacturing (SU)


Seminar on A.I. in Design and Manufacturing


Time: Every Wednesday from 4-5:30 during Spring Quarter.
Location: Terman Engineering Center, room 556, Stanford.

For further information contact:

Jay M. Tenenbaum, Consulting Professor, Computer Science
(415) 496-4699 or Tenenbaum@SRI-KL.


Purpose: To explore and stimulate the use of A.I. concepts and tools in
engineering.

This seminar will bring together engineers and computer scientists
interested in applying A.I. methods to engineering problems. We will
study the knowledge and reasoning processes used in designing and
manufacturing electronic and mechanical systems, and how they can be
codified for use in intelligent CAD/CAM systems.

Seminar Format:

An initial series of lectures, by distinguished A.I. researchers,
will describe ways in which engineering knowledge can be formalized,
and manipulated by a computer to solve design and manufacturing
problems. Subsequent lectures, by guest lecturers and students, will
present case studies drawn from the domains of electronic and
mechanical design, semiconductor fabrication, and process planning.
Seminal papers will be distributed and discussed in conjunction
with each lecture.

One unit of credit (pass/fail) will be granted for reading papers and
participating in class discussion. Students who elect to do a
programming project or an in-depth ontological study of some
engineering task will receive three units (graded).



Tentative Schedule (Subject to Change)

April 2 Course Introduction (Jay M. Tenenbaum)
Rule-based systems; Application to Heuristic Classification
(William Clancey)

9 Frames and Objects; Application to Modeling and Simulation
(Richard Fikes)

16 Logic; Application to Design Debugging, Diagnosis, And Test
(Michael Genesereth)

23 Prolog: Application to Design Verification (Harry Barrow)

30 Truth Maintainance; Application to Diagnosing Multiple Faults.
(Johann DeKleer)

May 7 Knowledge Engineering as Ontological Analysis (Pat Hayes)

14 Transformational Approaches to Synthesis; Applications to
Electronic and Mechanical Design (Cordell Green).

21 Modeling and Reasoning about Electronic Design:
Paladio (Harold Brown); Helios (Narinder Singh)

28 Modeling and Reasoning about Semiconductor Fabrication
(John Mohammed, M. Klein)

June 4 Applications of AI in Mechanical Design and Manufacture
The PRIDE Design System (Sanjay Mittal);
Video Tape on Expert Systems for Manufacturing (Mark Fox).


(Exam Week) Presentation of Student Projects

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

Date: 16 Mar 86 02:29:34 GMT
From: cbosgd!dayal@ucbvax.berkeley.edu (Umeshwar Dayal)
Subject: Conference - Object Oriented Database Systems

CALL FOR PAPERS

International Workshop on Object-Oriented Database Systems (OODBS)

September 23-26, 1986
Asilomar Conference Center, Pacific Grove, California


Sponsored by: Association for Computing Machinery -
SIGMOD
IEEE Computer Society - TC on Database
Engineering

In cooperation with: Gesellschaft fur Informatik, Germany
FZI at University of Karlsruhe, Germany
IIMAS, Mexico

Purpose:

To bring together researchers actively interested in specific con-
cepts for database systems that can directly handle objects of
arbitrary structure and complexity. Application environments for
which such characteristics are required include CAD, software
engineering, office automation, cartography and knowledge represen-
tation. Important issues include data/information models, transac-
tion mechanisms, integrity/consistency control, exception handling,
distribution, protection, object-oriented languages, architectural
issues, storage structures, buffer management, and efficient imple-
mentation.

Format: Limited attendance workshop. Participation is by invita-
tion only.

Everybody wishing to participate must submit a full paper that will
be reviewed by the program committee. Description of work in pro-
gress is encouraged and modifications to the submitted paper can be
made immediately after the workshop and prior to publication in
order to reflect the progress made during the time between submis-
sion and publication and the insights gained from the workshop.

Participants will be invited by the program committee based upon
the relevance of their interests/contributions. There will be
ample discussion time with presentations and special discussion
sessions. Proposals for discussion topics are invited.

Program committee:

K. Dittrich (FZI Germany)-chairman U. Dayal (CCA) - co-chairman
D. Batory (Univ. of Texas) M. Haynie (Amdahl)
A. Buchmann (Univ. of Mexico) D. McLeod (USC)

Conference Treasurer: D. McLeod

Local arrangments: M. Haynie

Publication:

All participants will be sent copies of the accepted papers prior
to the meeting. A book containing revised papers and recorded dis-
cussions (as far as justified by quality) may be published after
the workshop.

Important dates:

Submission of manuscripts: April 25, 1986
Notification of acceptance: June 15, 1986
(early notification via electronic mail)June 3, 1986
Submission of papers for preconference distribution:July 10, 1986

Mode of submission: Please mail 7 copies of manuscript to:

Umeshwar Dayal or Klaus Dittrich
CCA FZI
Four Cambridge Center Haid-und-Neu-Strasse 10-14
Cambridge, MA 02142 D-7500 Karlsruhe 1
USA Germany

dayal@cca-unix.arpa dittrich@Germany.arpa
Phone: +1 617/492-8860 Phone: +49 0721/69 06-0

Remember to include your electronic mail address for early notifi-
cation.

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

Date: Tue, 18 Mar 86 4:28:51 EST
From: "Dr. James Johannes" (UAH+ARO) <johannes@BRL.ARPA>
Subject: Conference - US ARMY (ARO) AI WORKSHOP


CALL FOR PARTICIPATION

Future Directions in June 17-19, 1986
Artificial Intelligence Hyatt Regency
Crystal City, VA
Workshop

Keynote Speaker: Sponsored by:
Honorable Jay R. Sculley Computer Science Program
Assistant Secretary of Army Army Research Office
Research, Development & Acquisition Research Triangle Pk
NC 27709-2211


You are invited to participate in the Workshop entitled "Future
Directions in Artificial Intelligence" to be held from June 17 to
June 19, 1986 at the Hyatt Regency - Crystal City, Virginia.
Presentations will focus on both theoretical work and experi-
mental results. Possible topics to be discussed include:

o Military Expert Systems
o Vision
o Image Processing
o Speech Technology
o Machine Translation

The workshop will involve invited overview papers, short
presentations on specific subjects or projects, and discussion
periods. Attendance will be limited to 100 participants with
about equal representation among military, academia, and
industry. Each participant will be a recognized expert in at
least one aspect of Artificial Intelligence.

Four copies of a 400-2000 word summary should be submitted by the
deadline to the Workshop Chairman. Some attendees will be
invited to make a presentation on one of the workshop topics. A
workshop proceedings will be published and will be mailed to all
the attendees.


Attendance limited to: 100
Presentation/participation Request due by: April 25, 1986
Notification of participation acceptance by: May 9, 1986
Camera-ready papers due by: June 5, 1986


Workshop Chairman: ARO Representative:

Prof. James D. Johannes Dr. C. Ronald Green
Computer Science Army Research Office
The University of Alabama in Huntsville P.O. Box 12211
Huntsville, AL 35899 Research Triangle Pk.
Tel: (205) 895-6255/6088 NC, 27709-2211
uucp: akgua!uahcs1!johannes Tel: (919) 549-0641
arpanet: johannes@brl arpanet: green@brl


Application for presentation/participation:
(Due by April 25, 1986)

Name: Dr/Mr/Ms/Miss/Mrs ________________________________________
Address: _______________________________________________________
_______________________________________________________
Telephone number: (_____)_______ - __________
E-Mail(arpanet/uucp)_________________________
Name of the Government Agency, University, or Company:


PROPOSED PRESENTATION INFORMATION
(include 400-2000 word summary)

Topic area:
( ) Military Expert Systems ( ) Vision ( ) Image Processing
( ) Speech ( ) Machine Translation ( ) Other - Specify _______

Overall presentation category:
( ) Theoretical ( ) Experimental ( ) Tutorial
( ) Applied Research ( ) Others

Military Application Area:

Title of proposed presentation:


PROPOSED ATTENDEE INFORMATION
Topic area:
( ) Military Expert Systems ( ) Vision ( ) Image Processing
( ) Speech ( ) Machine Translation ( ) Other - Specify _______

Past Accomplishments in the Artificial Intelligence areas:

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

End of AIList Digest
********************

← previous
next →
loading
sending ...
New to Neperos ? Sign Up for free
download Neperos App from Google Play
install Neperos as PWA

Let's discover also

Recent Articles

Recent Comments

Neperos cookies
This website uses cookies to store your preferences and improve the service. Cookies authorization will allow me and / or my partners to process personal data such as browsing behaviour.

By pressing OK you agree to the Terms of Service and acknowledge the Privacy Policy

By pressing REJECT you will be able to continue to use Neperos (like read articles or write comments) but some important cookies will not be set. This may affect certain features and functions of the platform.
OK
REJECT