Copy Link
Add to Bookmark
Report

Machine Learning List Vol. 4 No. 18

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

 
Machine Learning List: Vol. 4 No. 18
Thursday, Sept 10, 1992

Contents:

Backfitting
GAs and Breiman's algorithm
postdoc candidates sought
Machine Learning 9:2/3
REQUEST Multi-algorithm Machine Learning system?
The Third International Workshop on Inductive Logic Programming
Call for Papers: Intelligent Systems for Molecular Biology
Integrating AI Reasoning Systems and Hardware Description Languages
Final Reminder: AAI-XI CFP



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: 03 Sep 1992 18:02:41 +0200
Subject: Backfitting
From: TREVOR@uctvax.uct.ac.za


Tom Dietterich wrote:

> I recently read the following paper by Leo Breiman:
>
> Breiman, L. (1991) The $\Pi$ method for estimating multivariate
> functions from noisy data. {\it Technometrics, 33} (2), 125--160.
> With discussion.
>
> In this paper, Breiman presents a very neat technique called "back
> fitting"
that is a very general algorithm idea for improving greedy
> algorithms. ....

This article is indeed worth reading. I thought it worthwhile to point
out that "backfitting" has been around for quite a while.
Interesting to this audience should be the pioneering article "Projection
Pursuit Regression"
by Friedman and Stuetzle (1981), Journal of
the American Statistical Association, 76, 817-823. There is a
close connection between PPR and Neural Network models.
This article was the first to propose backfitting in the context
of nonparametric regression modelling, and led to its subsequent
use in many newer but related techniques. Hastie, Buja and
Tibshirani (1989), "Linear Smoothers and Additive Models", Annals
of Statistics, 17, 453-555, study backfitting in detail, and show
its relation to the classical Gauss-Seidel procedure in numerical
analysis for iteratively solving linear systems of equations.

Trevor Hastie, AT&T Bell Laboratories


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

Date: Tue, 8 Sep 92 12:35:44 EDT
From: spears@aic.nrl.navy.MIL
Subject: GAs and Breiman's algorithm

In response to:
> From: Tom Dietterich <tgd@icsi.berkeley.EDU>
> Subject: A neat idea from L. Breiman

> Suppose we are executing a greedy algorithm for some
> task, and at any given point in the process, we have already made
> decisions d_1, d_2, ..., d_{k-1} and we are about to make decision
> d_k. ...

> repeat until quiesence [sic]:
> for i from 1 to k-1 do
> "undo" decision d_i (holding all other decisions d_j, j<>i fixed)
> and re-make d_i to be the best decision (locally).


Researchers in the genetic algorithm (GA) community, in their
attempts to characterize what is easy and/or hard for a GA, have
been comparing the GA with algorithms similar to that described
above. The 1991 conference proceedings include a relevant
paper by Stewart Wilson, and one by Lawrence (Dave) Davis.

If we represent the set of decisions as a chromosome, Breiman's
algorithm is similar to a GA with a population of one chromosome
and, ofcourse, no crossover operator. Probabilistic mutation could
replace the deterministic local decisions, or in fact, one could
use a more deterministic mutation operator.

For example, if one knows that there are no more than n decisions
to be made for the task, one could code the chromosome as:

{d_0, d_1, ..., d_n}, with possible no-ops inserted if all n

decisions are not required. If a population of (> 1) chromosomes
is maintained, crossover could allow the construction of subsets
of good decisions, within a chromosome.

If it isn't clear that there are at most n decisions, one could
resort to variable length genetic algorithms.

Our GABIL project (w/ Ken De Jong) is one example of this approach.
GABIL represents DNF hypotheses (chromosomes) as variable length
sets of decision rules. GAs use selection to focus the search in
promising areas, and use crossover to locate groups of good
decision rules.

The cost/benefit tradeoffs of GAs vs "Breiman-style" algorithms
are yet to be fully determined, however.

Bill Spears
Diana Gordon


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

From: Raul Valdes-Perez <valdes@carmen.kbs.cs.cmu.EDU>
Date: Wed, 9 Sep 92 09:28:33 EDT
To: ml@ics.uci.edu
Subject: postdoc candidates sought

We are seeking candidates for a post-doctoral fellowship at Carnegie
Mellon University in the area of Computational Biology. The fellow
would carry out computational research on specific biological problems
in collaboration with members of the School of Computer Science, the
Center for Light Microscope Imaging and Biotechnology, and the
Department of Biological Sciences.

The ideal candidate would likely hold a recent Ph.D. in Computer
Science (e.g., Artificial Intelligence or Computer Vision), possess
some knowledge of Biology, especially Cell Biology, and demonstrate an
inclination to enter deeply into real-life problems drawn from the
natural sciences.

Inquiries to:

Dr. Raul Valdes-Perez FAX: 412 681 5739
School of Computer Science TEL: 412 268 7127
Carnegie Mellon University Internet: valdes@cs.cmu.edu
5000 Forbes Avenue
Pittsburgh, PA 15213

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

Date: Wed, 9 Sep 92 16:49:50 PDT
From: Tom Dietterich <tgd@chert.CS.ORST.EDU>
Subject: Machine Learning 9:2/3

Machine Learning
July 1992, Volume 9, Issues 2/3

Special Issue on Computational Learning Theory

Introduction
J. Case and A. Blumer
Lower Bound Methods and Separation Results for On-Line Learning Models
W. Maass and G. Turan
Learning Conjunctions of Horn Clauses
D. Angluin, M. Frazier, and L. Pitt
A Learning Criterion for Stochastic Rules
K. Yamanishi
On the Computational Complexity of Approximating Distributions by
Probabilistic Automata
N. Abe and M. K. Warmuth
A Universal Method of Scientific Inquiry
D.N. Osherson, M. Stob, and S. Weinstein


Subscriptions - Volume 8-9 (8 issues) includes postage and handling.
$140 Individual
$88 Member AAAI
$301 Institutional

Kluwer Academic Publishers
P.O. Box 358
Accord Station
Hingham, MA 02018-0358 USA

or

Kluwer Academic Publishers Group
P.O. Box 322
3300 AH Dordrecht
THE NETHERLANDS

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

Date: Wed, 2 Sep 1992 10:51:22 -0600
From: Dick Jackson <Dick_Jackson@qm.ibd.nrc.ca>
Subject: REQUEST Multi-algorithm Machine Learning system?

Our Informatics group has been discussing the need for a software
system for doing Multivariate Analysis, primarily for classification
and clustering tasks, making techniques from different areas of Machine
Learning available to the user.

What I would like to know is: has something of this kind been developed
already? Many excellent individual machine-learning programs are
available from different sources, but has anyone made a system which
allows combination and comparison of different algorithms?

In more detail, we would want the system to include:

A. Pre-processing of raw data file:
- provide a means for choosing a sequence of options such as:
- normalizing selected variables
- filling in missing data
- creating new variables from existing ones
- performing transforms via Principal Component Analysis, etc.
- splitting data into 'training set' and 'test set'
- saving resulting dataset with pre-processing details

B. Dataset Analysis
- following with the dataset above, allow any of a number of types of
analysis, each of which result in a clustering or classification
'system', such as:
- inductive learning, giving a decision tree or other representation
- connectionist, giving a trained neural net
- LDA, genetic algorithms, fuzzy clustering...
(incorporating software from willing sources)
- parameters/options for these analyses can be numerous, but
heuristics can give a good first-attempt at parameter choice
- interactive displays may be needed for some
- end results to be saved for future use

C. Test/Use of classifier systems:
- pass test data through resulting classifier systems, giving reports
of accuracy, sensitivity, specificity, etc.
- pass new unclassified data through classifiers, giving predicted
classes (with confidence estimates?)

D. Meta-analysis:
- based on reports from the previous stage, devise more robust
classification systems incorporating multiple techniques

The target user could be a medical researcher, not a programmer, so a
clear graphical user interface is of high importance.

It is clear that much of part A is seen in some of the better
statistical packages, but what about the machine learning techniques?
Is anyone developing a multiple-technique 'workbench' like this? If
not, we might be interested in starting up such a project.

I welcome any comments on this topic, please reply to me directly. If
there is enough interest in a summary, I will provide it.

Thanks for your time,

-Dick

Dick Jackson
Institute for Biodiagnostics National Research Council Canada
Winnipeg, Manitoba Dick_Jackson@ibd.nrc.ca


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

From: Steve Muggleton <steve@turing.ac.UK>
Date: Sat, 5 Sep 92 17:17:54 BST
Subject: The Third International Workshop on Inductive Logic Programming

THE THIRD INTERNATIONAL WORKSHOP ON
INDUCTIVE LOGIC PROGRAMMING (ILP93)
1-3 April, 1993
Conference Hall Bistro Toplice,
64260 Bled,
Slovenia.

This workshop is the third in a series of International workshops on
Inductive Logic Programing. The workshop will bring together an
international group of researchers in the field. Inductive Logic
Programming is a research area spawned by Machine Learning and Logic
Programming. While the influence of Logic Programming has encouraged
the development of strong theoretical foundations, the new area is
inheriting its experimental orientation from Machine Learning.

Unlike the first two ILP workshops, the third international workshop
will not be by invitation only, but open to all submissions. Papers are
encouraged in, though not restricted to, the following areas.

Theory. Papers should either 1) prove new results concerning programs
which use inductive learning to construct first or higher order
logic descriptions or 2) discuss the relationship of
Inductive Logic Programming to other theoretical
areas such as Non-Monotonic Logic or Abductive Reasoning.
Learnability results and theoretical
investigations of predicate invention are
especially welcome.
Implementation. Details of inductive algorithms. Time complexity results
should be included.
Experimentation. Experimental results should be tabulated with appropriate
statistics. Sufficient details should be included to allow
reproduction of results. Comparative studies of different algorithms
running on the same examples, using the same background knowledge, are
especially welcome.

Papers will be assessed by the following international program committee
Charles Ling (Canada) Fumio Mizoguchi (Japan)
Stephen Muggleton (UK) Luc de Raedt (Belgium)

The workshop will immediately precede the European Conference on
Machine Learning (ECML-93) which will be held on 5,6,7 April in Vienna.
Thus attendees are encouraged to take part in both ILP93 and the larger
ECML-93 conference. Transport of ILP93 participants from Bled to Vienna
will be organised. PARTICIPANTS MUST FIND THEIR OWN FUNDS FOR TRAVEL.

Organisation
Program Chair: Stephen Muggleton,
Programming Research Group,
Oxford University Computing Laboratory,
11 Keble Road,
Oxford,
OX1 3QD,
U.K.
Fax: +44-865-273839 Tel: +44-865 273838

Local Chair: Nada Lavrac,
Jozef Stefan Institute,
Jamova 39,
61111,
Ljubljana,
Slovenia.
Email: nada.lavrac@ijs.ac.mail.yu
Fax: +38-61-161-029 Tel: +38-61-159-199

Deadlines

Printed papers to be included in the proceedings of the workshop must
be received by the PROGRAM CHAIR no later than 15th January, 1993.
Authors will be informed of acceptance by 19th February, 1993.
Camera-ready copy should then be received by the local chair
by 5th March, 1993. To ensure that papers in the proceedings
are readable, only hard-copy papers will be accepted, not papers sent
by email or fax. Papers received after the deadline will not be
included in the proceedings.

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

Date: Tue, 8 Sep 92 10:42:31 -0400
From: Larry Hunter <hunter@nlm.nih.GOV>
Subject: Call for Papers: Intelligent Systems for Molecular Biology


***************** CALL FOR PAPERS *****************

The First International Conference on
Intelligent Systems for Molecular Biology

July 7-9, 1993
Washington, DC

Organizing Committee Program Committee
--------------------- -----------------------------
Lawrence Hunter, D. Brutlag, Stanford
National Library of Medicine B. Buchanan, U. of Pittsburgh
C. Burks, Los Alamos
David Searls, F. Cohen, UC-SF
University of Pennsylvania C. Fields, TIGR
M. Gribskov, UC-SD
Jude Shavlik, P. Karp, SRI
University of Wisconsin A. Lapedes, Los Alamos
R. Lathrop, MIT
Schedule C. Lawrence, Baylor
--------------------- M. Mavrovouniotis, U-Md
Papers and Tutorial G. Michaels, NIH/DCRT
Proposals Due: H. Morowitz, George Mason
February 15, 1993 K. Nitta, ICOT
M. Noordewier, Rutgers
Replies to Authors: R. Overbeek, Argonne
March 29, 1993 C. Rawlings, ICRF
D. States, NLM, NIH
Revised Papers Due: G. Stormo, U. of Colorado
April 26, 1993 E. Uberbacher, Oak Ridge
D. Waltz, Thinking Machines

Sponsors: American Association for Artificial Intelligence,
National Library of Medicine

The First International Conference on Intelligent Systems for
Molecular Biology will take place in Washington, DC, July 7-9,
1993. The conference will bring together scientists who are
applying the technologies of artificial intelligence, robotics,
neural networks, massively parallel computing, advanced data
modelling, and related methods to problems in molecular biology.
Participation is invited from both producers and consumers of any
novel computational or robotic system, provided it supports a
biological task that is cognitively challenging, involves a
synthesis of information from multiple sources at multiple
levels, or in some other way exhibits the abstraction and
emergent properties of an "intelligent system." The three-day
conference, to be held in the attractive conference facilities of
the Lister Hill Center, National Library of Medicine, National
Institutes of Health, will feature both introductory tutorials
and original, refereed papers, to be published in an archival
Proceedings. The conference will immediately precede the
Eleventh National Conference of the American Association for
Artificial Intelligence, also in Washington.

Papers should be 12 pages, single-spaced and set in 12 point
type, including title, abstract, figures, tables, and
bibliography. The first page should give keywords, postal and
electronic mailing addresses, telephone, and FAX numbers.
Submit 6 copies to the address shown. For more information,
contact ISMB@nlm.nih.gov.

Jude Shavlik
Computer Sciences Dept
University of Wisconsin
1210 W. Dayton Street
Madison, WI 53706



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

Date: Wed, 9 Sep 92 20:44:15 CDT
From: Keith Levi <levi@miu.EDU>
Subject: Integrating AI Reasoning Systems and Hardware Description Languages

**************************************************************************

APPLICATIONS OF AI XI: Knowledge-Based Systems in Aerospace & Industry
=====================================================================

SPECIAL SESSION:
INTEGRATING AI REASONING SYSTEMS AND HARDWARE DESCRIPTION LANGUAGES


CALL FOR PAPERS

Authors are invited to submit draft papers for this special session that
will be held at the Applications of Artificial Intelligence XI Conference.
The focus of this year's conference is on industrial and aerospace
applications of AI, machine learning, and reasoning systems. The
conference will take place April 12-16, 1993 in Orlando, Florida. This
special session will be scheduled for a half-day sometime during the
conference. Further details on the conference are given in the conference
announcement attached to the end of this special session description.

This special session will focus on issues involved in 'knowledge sharing'
between AI reasoning systems and equipment descriptions, specifications and
models. Since each source contains information of interest to the other,
the ability to establish interactions between them should have great
benefits for both.

The obvious benefit to AI systems is a partial solution to the age-old
knowledge acquisition bottleneck. Knowledge-based systems, especially
reasoning systems and many machine learning techniques, typically require
extensive knowledge about the domain in which they are to operate. The
required breadth and depth of this prerequisite knowledge is especially
challenging in complex, real-world domains such as industrial and aerospace
applications. On the other hand, it is commonplace in these domains for
equipment to be well documented, both before and after manufacture, with
detailed specifications about its functionality and performance
characteristics. It will soon be the case that most of these equipment
specifications will be written and developed as executable software
simulations in hardware description languages such as the VHSIC Hardware
Description Language (VHDL) and Verilog.

Clearly, it would be of great benefit for knowledge-based systems to be
able to obtain at least some of their prerequisite knowledge from such
sources. As one prominent researcher in the area of explanation based
learning speculated: "We foresee a future in which manufacturers of
component equipment themselves provide descriptions, in some standard
knowledge-based formalism, of the functionality of their product just as
today they provide technical descriptions in a form understandable to
[equipment] designers. As the manufacturer makes available refined
versions of installed equipment, the old knowledge-based description of the
component is simply supplanted with the new. The knowledge engineer need
only oversee incorporation of the new knowledge insuring that there are no
negative interactions that harm overall system performance."
(Jerry
DeJong, March, 1992)

There are also great potential benefits for hardware designers to
integrating AI systems with hardware description languages and simulations.
These potential benefits come from the fact that AI systems are much better
sources for representing and reasoning about high-level, integrated system
performance descriptions. Such high-level representations and reasoning
can be used to derive requirements around which systems should be designed.
This sort of reasoning can also be used in verifying that integrated
systems of components will perform as required. Finally, such high-level
reasoning can effectively be used to guide efficient resource usage or fast
reconfiguration of systems of components.

This special session will be devoted to exploring issues that arise in
integrating AI reasoning systems with descriptions, models, specifications
or simulations of equipment. We are especially soliciting papers reporting
on current or recent work integrating AI reasoning systems with hardware
description languages, from either of the perspectives described above. We
also encourage papers on directly relevant topics such as knowledge sharing
research, multilevel and integrated reasoning systems, variable resolution
modeling, reasoning over multiple models, automated simulation design and
analysis, and deriving hardware requirements from high-level AI reasoning
systems.

Submission Guidelines:

To submit a paper, send four copies not exceeding 10 pages single-spaced
(approx. 5000 words) including figures and bibliography by October 5, 1992
to the following address.

SPECIAL SESSION
c/o Chris Miller
Honeywell Systems and Research Center
3660 Technology Drive, MN65-2500
Minneapolis, MN 55418

We will review your paper and notify you of acceptance by 10 December.
Camera-ready papers (5000 words) will be due Jaunary 18, 1993. We
encourage prospective authors to contact any of the session organizers to
discuss topics before submitting full papers.


Session Organizers

Keith Levi email: levi@miu.edu
Computer Science Department telephone: 515 472-1103
Maharishi International University
Fairfield, IA

Chris Miller email: cmiller@src.honeywell.com
Honeywell Systems and Research Center telephone: 612 782-7484
Minneapolis, MN

Dale Moberg email: moberg@cis.ohio-state.edu
Laboratory for Artificial Intelligence telephone: 614 292-8578
Research
Ohio State University
Columbus, OH

Fred Rose email: rose@src.honeywell.com
Honeywell Systems and Research Center telephone: 612 782-7484
Minneapolis, MN


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

Date: Tue, 8 Sep 92 15:03:28 PDT
From: Usama Fayyad <fayyad@ai-cyclops.jpl.nasa.GOV>
Subject: Final Reminder: AAI-XI CFP

______________________________________________________________________________

FINAL CALL FOR PAPERS -- submission due date 9/14/92 -- FINAL CALL FOR PAPERS
______________________________________________________________________________


APPLICATIONS OF AI (XI): Knowledge-Based Systems in Aerospace & Industry
========================================================================

April 12-14, 1993
Marriott's Orlando World Center
Resort and Convention Center
Orlando, Florida, U.S.A.


The Eleventh Applications of Artificial Intelligence Conference will be
held April 12-14 in Orlando, FL. We invite you to submit a paper by the
deadline of Sept. 14, 1992. Details of areas and deadlines given below.

Conference Co-Chairs:
Usama M. Fayyad Ramasamy Uthurusamy
Jet Propulsion Lab General Motors Research Laboratories
California Institute of Technology

This year we will focus on techniques and applications that deal with
actual industrial and aerospace applications of AI, machine learning,
and reasoning systems.

Topics of interest include but are not limited to:

1. Machine Learning
2. Industrial and Aerospace Applications
3. Diagnostic Systems
4. Knowledge Acquisition and Refinement
5. Knowledge Based Systems: Verification and Validation
6. Manufacturing Systems
7. Case-Based Reasoning
8. Functional Reasoning
9. Model-Based and Qualitative Reasoning
10. Multilevel and Integrated Reasoning Systems
11. Planning and Scheduling
12. Design
13. Training and Tutoring Systems
14. Intelligent Interfaces and Natural Language Processing
15. Intelligent Database Systems
16. Parallel Architectures

In addition there will be 2-3 plenary sessions, and one or more panel
discussions. We also solicit suggestions for special sessions (e.g.,
Case-Based Tutoring, Reactive Planning in Space Missions). A one-page
description of such a suggestion should be sent to the Conference
Chairs, who will then forward it to appropriate members of the Program
Committee for evaluation. Selection will be based on how well the
topic relates to the general theme of the conference, and the level of
interest it is likely to generate.

To submit a paper, send four copies of a complete paper not exceeding 10 pages
single-spaced (approx. 5000 words) including figures and bibliography by
September 14, 1992 to:

Applications of AI XI: KBS
SPIE, P.O. Box 10
1000 20th Street
Bellingham, WA 98225.

Tele: (206)-676-3290; Telefax: (206)-647-1445.

Submissions will be reviewed by at least two members of the program
committee and reviews will be returned to the authors. It is
important that each paper clearly state the problem which is being
addressed, the contribution that has been made, and the relation to
the current state of the art.

The program committee and conference chairs will make a selection of the best
papers accepted, and these authors will be invited to submit a revised version
of their paper to one or more special issues of journals in AI (to be decided
later).

Papers submitted to the Knowledge-Based Systems conference should not also be
submitted to the Machine Vision & Robotics conference of Applications of AI XI.
Questions about which conference is most suitable for a particular paper
should be directed to the program chairmen.


IMPORTANT DATES: PAPERS DUE: September 14, 1992.
ACCEPT/REJECT LETTERS SENT BY: November 20, 1992
CAMERA-READY PAPERS (5000 words) DUE: January 18, 1993.
CONFERENCE DATES: April 12-16, 1993.

Further questions may be directed to (e-mail preferred):

Dr. Usama Fayyad Dr. Ramasamy Uthurusamy
AI Group M/S 525-3660 Computer Science Department
Jet Propulsion Lab General Motors Research Labs
California Institute of Technology 30500 Mound Rd.
Pasadena, CA 91109 Warren, MI 48090-9055

phone: (818) 306-6197 phone: (313) 986-1989
fax: (818)-306-6912. fax: (313) 986-9356
e-mail: Fayyad@aig.jpl.nasa.gov e-mail: Samy@gmr.com


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

End of ML-LIST (Digest format)
****************************************

← 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