Copy Link
Add to Bookmark
Report

Machine Learning List Vol. 4 No. 08

eZine's profile picture
Published in 
Machine Learning List
 · 11 months ago

 
Machine Learning List: Vol. 4 No. 8
Thursday, April 9, 1992

Contents:
ML93
Employment Opportunity at JPL
U Texas/Austin FTP Publication and Software Repository
COGANN-92
3RD ASIS SIG/CR CLASSIFICATION RESEARCH WORKSHOP

The Machine Learning List is moderated. Contributions should be relevant to
the scientific study of machine learning. Mail contributions to ml@ics.uci.edu.
Mail requests to be added or deleted to ml-request@ics.uci.edu. Back issues
may be FTP'd from ics.uci.edu in pub/ml-list/V<X>/<N> or N.Z where X and N are
the volume and number of the issue; ID: anonymous PASSWORD: <your mail address>

------------------------------
Date: Thu, 9 Apr 92 09:41:06 EDT
From: utgoff%iron@cs.umass.EDU
Subject: ML93

The Tenth International Conference on Machine Learning will be
held at the University of Massachusetts at Amherst in late
June 1993. Send comments, questions, or suggestions to
"ml93@cs.umass.edu".

------------------------------
Date: 9 Apr 92 11:16:57 U
From: RDoyle <rdoyle@isd.jpl.nasa.GOV>
Subject: Employment Opportunity at JPL

REGARDING Artificial Intelligence Group_
Artificial Intelligence Group
Jet Propulsion Laboratory
California Institute of Technology

Employment Opportunities

The Artificial Intelligence Group at JPL is seeking candidates with the
following qualifications and experience:

o At the Ph.D. level, a degree in Computer Science or
Engineering is required, with an emphasis on Artificial Intelligence.
Ideal candidates will have experience leading a small research team
and be prepared to implement software to solve significant AI
problems. Research experience in one of the following areas is
preferred: 1) model-based reasoning, 2) machine learning, 3) planning
& scheduling. Candidates with other research backgrounds also will be
considered. Publication of research results in major conferences and
journals will be required. A Ph.D. level candidate is also expected
to prepare proposals to pursue funding opportunities.

o At the M.S. level, a degree in Computer Science or
Engineering, programming skills in LISP and C, and knowledge of Unix
are required; 2-4 yrs experience and some research background
preferred.

o At the B.S. level, a degree in Computer Science or
Engineering, programming skills in LISP and C, and knowledge of Unix
are required; 1-2 yrs experience preferred.

If you are interested in one of these positions, please forward your resume or
CV to:
Richard J. Doyle
Supervisor, Artificial Intelligence Group
Jet Propulsion Laboratory, MS 525-3660
California Institute of Technology
4800 Oak Grove Drive
Pasadena, California 91109-8099

818 306-6149; 818 306-6912 fax email: rdoyle@aig.jpl.nasa.gov

An Equal Opportunity Employer

------------------------------
From: Raymond Mooney <mooney@cs.utexas.EDU>
Date: Tue, 31 Mar 1992 13:57:28 -0600
Subject: U Texas/Austin FTP Publication and Software Repository

UT MACHINE LEARNING ARCHIVE
Copies of publications and software developed by the machine learning group at
the University of Texas at Austin are now available via anonymous FTP from
cs.utexas.edu in the directory pub/mooney. The various programs and papers are
listed below.


ABOUT THIS ARCHIVE
The archive is divided into separate directories for papers and code. All
publications are stored in a compressed Postscript format, and should be
printable (after uncompressing) by any standard method for printing postscript
files. Each directory contains a README file with more details. Also, the
papers directory contains an ABSTRACTS file listing abstracts for all the
papers.


SOFTWARE SYSTEMS (all code is in Common Lisp)
* AQ
* Backpropagation
* COBWEB
* EGGS
* FOIL (Common Lisp and Prolog versions)
* Fringe
* ID3
* Perceptron
* UNIMEM
* Version Space
* k nearest neighbor algorithm
* simple Bayes independence classification system
* software for encoding multi-value features into binary
* a "universal tester" program
(NOTE: the universal tester is automatic testing software for running
learning curves that compare multiple systems and utilities for plotting
and statistically evaluating the results.)


PAPERS
aaai90.ps On the Role of Coherence in Abductive Explanation.
aaai91.ps An Efficient First-Order Horn-Clause Abduction System
Based on the ATMS.
iou-mlj.ps Induction Over the Unexplained: Using Overly-General
Domain Theories to Aid Concept Learning.
either-aij.ps Theory Refinement Combining Analytical and Empirical
Methods.
category-chapter.ps Integrating Theory and Data in Category Learning.
ml4-chapter.ps A Multistrategy Approach to Theory Refinement.
spring-symp-92.ps Batch versus Incremental Theory Refinement.
ilp-92.ps Automated Debugging of Logic Programs via Theory
Revision.
threvpac.ps A Preliminary PAC Analysis of Theory Revision.
cogsci-92.ps Using Theory Revision to Model Students and Acquire
Stereotypical Errors.


PAPERS COMING SOON
Learning Relations by Pathfinding
(to appear in AAAI-92)
Combining Symbolic and Neural Learning to Revise Probabilistic Theories
(Submitted to 1992 Machine Learning Workshop on Integrated Learning)
Speeding up Logic Programs by Combining EBG and FOIL
(Submitted to 1992 Machine Learning Workshop on Speedup Learning)


HOW TO DOWNLOAD
All files are retrievable using anonymous FTP from cs.utexas.edu. Here is a
sample session showing how to download a paper.

(1) To get to our machine

unix> ftp cs.utexas.edu
Name: annonymous
Password: your-login-name

(2) Get to the right directory

ftp> cd pub/mooney/papers

(3) To set up binary mode so the file can be transferred
correctly (as opposed to ascii mode)

ftp> binary

(4) Copy the file

ftp> get papername.ps.Z

(5) Quit ftp; go back to local machine

ftp> quit

(6) Uncompress the file, then print it with laser printer

unix> uncompress papername.ps.Z
unix> lpr -P <laser-printer> papername.ps

------------------------------
Date: Mon, 23 Mar 92 14:06:27 EST
From: Phil Smith <psmith@magnus.acs.ohio-state.EDU>
Subject: 3RD ASIS SIG/CR CLASSIFICATION RESEARCH WORKSHOP

CALL FOR PARTICIPATION
3RD ASIS SIG/CR CLASSIFICATION RESEARCH WORKSHOP

The American Society for Information Science Special Interest
Group on Classification Research (ASIS SIG/CR) invites
submissions for the 3rd ASIS Classification Research Workshop,
to be held at the 55th Annual Meeting of ASIS in Pittsburgh,PA.
The workshop will take place Sunday, October 25th, 1992, 8:30
a.m. - 5:00 p.m. ASIS `92 continues through Thursday, October
29th.

The CR Workshop is designed to be an exchange of ideas among
active researchers with interests in the creation, development,
management, representation, display, comparison, compatibility,
theory, and application of classification schemes. Emphasis will
be on semantic classification, in contrast to statistically based
schemes. Topics include, but are not limited to:

Warrant for concepts in classification schemes * Concept
acquisition * Basis for semantic classes * Automated
techniques to assist in creating classification schemes *
Statistical techniques used for developing explicit
semantic classes * Relations and their properties *
Inheritance and subsumption * Knowledge representation
schemes * Classification algorithms * Procedural
knowledge in classification schemes * Reasoning with
classification schemes * Software for management of
classification schemes * Interfaces for displaying
classification schemes * Data structures and programming
languages for classification schemes * Image
classification * Comparison and compatibility between
classification schemes * Applications such as subject
analysis, natural language understanding, information
retrieval, expert systems.

The CR Workshop welcomes submissions from various disciplines. Those
interested in participating are invited to submit a short (1-2 page
single-spaced) position paper summarizing substantive work that has
been conducted in the above areas or other areas related to semantic
classification schemes, and a statement briefly outlining the reason
for wanting to participate in the workshop. Submissions may include
background papers as attachments. Participation will be of two kinds:
presenter and regular participant. Those selected as presenters will
be invited to submit expanded versions of their position papers and to
speak to those papers in brief presentations during the workshop. All
position papers (both expanded and short papers) will be published in
proceedings to be distributed prior to the workshop. The workshop
registration fee is $35.00, which includes lunch and refreshments.

Submissions should be made by email, or diskette accompanied by paper
copy, or paper copy only (fax or postal) to arrive by May 15, 1992 to:

Raya Fidel, Graduate School of Library and Information Science,
University of Washington, FM-30, Seattle, WA 98195; Internet:
fidelr@u.washington.edu
Phone: 206-543-1888; Fax: 206-685-8049
------------------------------
Date: Mon, 30 Mar 92 11:42:49 EST
From: Dave Schaffer <ds1@philabs.philips.COM>
Subject: COGANN-92

Workshop Announcement

COGANN-92

A Workshop on Combinations of
Genetic Algorithms and Neural Networks

June 6, 1992
Sheraton Inner Harbor Hotel
Baltimore, Maryland, USA

Sponsored by the IEEE Neural Networks Council
with the cooperation of the International Society for Genetic Algorithms

The day before the start of IJCNN-92, a one day workshop is
scheduled on Combinations Of Genetic Algorithms and Neural
Networks. Both of these computational paradigms are inspired by
information processing schemes used by nature, but they typically
have vastly different time constants. Recently, researchers have
begun experimenting with combining them into adaptive learning and
optimization systems with new capabilities. The goal of the
workshop is to bring together researchers to share concepts,
experience and recent research results. The IEEE Computer Society
Press will publish selected papers in a post-proceedings to appear
within a few months of the workshop.


The COGANN-92 Conference Committee

J. David Schaffer Philips Laboratories Conference Chair
Darrell Whitley Colorado State Univ. Program Chair
Gilbert Syswerda BBN Laboratories Finance Chair
Frank B. Weiskopf Johns Hopkins Univ. Publicity
Richard K. Belew Univ. of California at San Diego
Donald Brown Univ. of Virginia
Thomas P. Caudell Boeing Computer Services
Lawrence Davis Tica Associates
Russell Eberhart Research Triangle Inst.
Steven Harp Honeywell Inc.
Kendall Nygard North Dakota State Univ.

REGISTRATION

All participants must register (administration of this workshop is
independent of the administration of IJCNN-92). The registration
fees include a copy of the post-proceedings (except "Student: No
Proceedings" option) to be mailed to you when it is published.
Lunch is also included. Students are requested to supply proof of
student status along with their registration form. Those who paid
full registration to ICGA-91 are accorded ISGA membership. Hotel
reservations may be handled through the Housing Bureau IJCNN'92 or
directly with an area hotel.

COGANN-92
Preliminary Schedule

8:30 - 9:00 J.D. Schaffer
Genetic Algorithms and Neural Networks: The State of the
Art

9:00 - 9:30 D. Whitley
Genetic Algorithms and Neural Networks: Challenges and
Opportunities

9:40 - 10:10 J. Elias
Genetic Generation of Connection Patterns for a Dynamic
Artificial Neural Network

10:10 - 10:30 BREAK

10:30 - 10:55 F. Gruau
Genetic Synthesis of Boolean Neural Networks with a Cell
Rewriting Developmental Process

10:55 - 11:20 K. Lindgren, A. Nilsson, M. Nordahl and I. Rade
Regular Language Inference Using Evolving Neural
Networks

11:20 - 11:55 R. Eberhart
The Role of Genetic Algorithms in Neural Network
Explanation Facilities and Query-Based Learning

11:55 - 12:20 C. Schizas, C.Pattichis, R. Livesay and L. Middleton
Neural Networks, Genetic Algorithms and K-Means
Algorithm

12:20 - 1:30 LUNCH

1:30 - 3:00 Posters Session:
Approximately 12 poster will be presented. Authors will
be available to discuss their work.

3:00 - 4:00 Posters and Working Groups:
Individuals working in similar areas can discuss current
research results and identify promising future
directions.

4:00 - 5:30 Panel Discussion and Wrap-up
Working groups will summarize their conclusions.



Registration Form COGANN-92 June 6, 1992

Last Name____________________________First Name___________________Middle________________

Professional Affiliation:_______________________________________________________________

Mailing address:________________________________________________________________________

________________________________________________________________________________________

________________________________________________________________________________________

e-mail:______________________________telephone:___________________FAX:__________________

IEEE membership number: _____________________________ Did you attend ICGA-91? __________

Have you any dietary restrictions? _____________________________________________________

Do you wish to receive information on Baltimore area hotels? ______________________

____IEEE/ISGA members (early) . . . . . $75 ____ non-members (early) . . . . . $85
____IEEE/ISGA members (after May 29). . $85 ____ non-members (after May 29). . $95
____Student with Proceedings. . . . . . $65 ____ Student: No Proceedings . . . $40

Make checks or money orders (US $ only) payable to COGANN-92 and send to:

Mr. Gilbert Syswerda, ISGA, 53 Lake Street, Winchester, MA 01890
------------------------------
END of ML-LIST 4.8

← 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