Copy Link
Add to Bookmark
Report
Neuron Digest Volume 12 Number 29
Neuron Digest Thursday, 30 Dec 1993 Volume 12 : Issue 29
Today's Topics:
Administrivia - Digest on Holiday
New volume on Oscillations, Chaos, and Sequence Processing
Connectionist model monograph
technical report available ...
Proceedings available
Re: Where Can I Get Source for "NEURON"?
Submission to Neuron Request
MIT Press Book Announcement
Send submissions, questions, address maintenance, and requests for old
issues to "neuron-request@psych.upenn.edu". The ftp archives are
available from psych.upenn.edu (130.91.68.31). Back issues requested by
mail will eventually be sent, but may take a while.
----------------------------------------------------------------------
Subject: Administrivia - Digest on Holiday
From: "Neuron-Digest Moderator, Peter Marvit" <neuron@psych.upenn.edu>
Date: Thu, 30 Dec 93 01:29:50 -0500
Dear Readers,
Your Moderator will be traveling until Jan 12 and so the Digest will be
on holiday until that date (or a couple of days after I catch up).
Obviously, I will not be reading or responding to email until I return.
My best wished to all for a healthy holiday season and prosperous New
Year.
Cheers,
Peter
: Peter Marvit, Neuron Digest Moderator <neuron-request@psych.upenn.edu> :
: Courtesy of the Psychology Department, University of Pennsylvania :
: 3815 Walnut St., Philadelphia, PA 19104 w:215/898-6274 h:215/387-6433 :
------------------------------
Subject: New volume on Oscillations, Chaos, and Sequence Processing
From: yifanhan@helix.nih.gov (yi-fan han)
Date: Fri, 20 Aug 93 12:57:04 -0500
For your information, the following is now available from
IEEE Computer Society Press:
"Artificial Neural Networks: Oscillations, Chaos, and Sequence Processing"
Lipo Wang and Daniel L. Alkon (eds.)
which includes an introduction and a collection of papers in the area.
It may be ordered from IEEE Computer Society, 10662 Los Vaqueros
Circle, Los Alamitos, CA 90720-1264; phone 1-800-CS-BOOKS
FAX (714) 821-8380.
-- Yifan
------------------------------
Subject: Connectionist model monograph
From: rsun@athos.cs.ua.edu (Ron Sun)
Date: Thu, 19 Aug 93 21:35:53 -0600
A book (monograph) on connectionist models is available now
from John Wiley and Sons, Inc. titled:
===================================================================
Integrating Rules and Connectionism for Robust Commonsense Reasoning
by: Ron Sun
Assistant Professor
Department of Computer Science
The University of Alabama
Tuscaloosa, AL 35487
===================================================================
Anyone interested in the book should contact John Wiley and Sons, Inc.
at 1-800-call-wiley
- ------------------------------------------------------------------
A brief description is as follows:
One of the more difficult problems for artificial intelligence research
is the problem of modeling commonsense reasoning. Traditional models
have great difficulties in capturing the flexible and robust nature of
commonsense reasoning. This book attempts to tackle this problem by
adopting innovative approaches. In a nutshell, it is concerned with
understanding and modeling commonsense reasoning with a combination of
rules and similarities, under a connectionist rubric.
The book surveys the areas of reasoning, connectionist models, inheritance,
causality, rule-based systems, and similarity-based reasoning; it introduces
a new framework and a novel connectionist architecture for modeling
commonsense reasoning that synthesizes some of these areas.
Along with this framework, a set of interrelated new ideas regarding modeling
commonsense reasoning is discussed in the book, which are very relevant to the
current artificial intelligence and cognitive science research
and the on-going methodological debate.
- ------------------------------------------------------------------
Table of Content
Foreword (by David Waltz, NEC Research Institute)
Preface
1 Introduction
1.1 Overview
1.2 Commonsense Reasoning
1.3 The Problem of Common Reasoning Patterns
1.4 What is the Point?
1.5 Some Clarifications
1.6 The Organization of the Book
1.7 Summary
2 Accounting for Commonsense Reasoning: A Framework with Rules and Similarities
2.1 Overview
2.2 Examples of Reasoning
2.3 Patterns of Reasoning
2.4 Brittleness of Rule-Based Reasoning
2.5 Towards a Solution
2.6 Some Reflections on Rules and Connectionism
2.7 Summary
3 A Connectionist Architecture for Commonsense Reasoning
3.1 Overview
3.2 A Generic Architecture
3.3 Fine-Tuning --- from Constraints to Specifications
3.4 Summary
3.5 Appendix
4 Evaluations and Experiments
4.1 Overview
4.2 Accounting for the Reasoning Examples
4.3 Evaluations of the Architecture
4.4 Systematic Experiments
4.5 Choice, Focus and Context
4.6 Reasoning with Geographical Knowledge
4.7 Applications to Other Domains
4.8 Summary
4.9 Appendix: Determining Similarities and CD representations
5 More on the Architecture: Logic and Causality
5.1 Overview
5.2 Causality in General
5.3 Shoham's Causal Theory
5.4 Defining FEL
5.5 Accounting for Commonsense Causal Reasoning
5.6 Determining Weights
5.7 Summary
5.8 Appendix: Proofs For Theorems
6 More on the Architecture: Beyond Logic
6.1 Overview
6.2 Further Analysis of Inheritance
6.3 Analysis of Interaction in Representation
6.4 Knowledge Acquisition, Learning, and Adaptation
6.5 Summary
7 An Extension: Variables and Bindings
7.1 Overview
7.2 The Variable Binding Problem
7.3 First-Order FEL
7.4 Representing Variables
7.5 A Formal Treatment
7.6 Dealing with Difficult Issues
7.7 Compilation
7.8 Correctness
7.9 Summary
7.10 Appendix
8 Reviews and Comparisons
8.1 Overview
8.2 Rule-Based Reasoning
8.3 Case-Based Reasoning
8.4 Connectionism
8.5 Summary
9 Conclusions
9.1 Overview
9.2 Some Accomplishments
9.3 Lessons Learned
9.4 Existing Limitations
9.5 Future Directions
9.6 Summary
References
- ---------------------------------------------------------------------
------------------------------
Subject: technical report available ...
From: ww@neuroinformatik.ruhr-uni-bochum.de (Willfried Wienholt)
Date: Thu, 14 Oct 93 09:25:26 +0700
A postscript copy of the following Internal Report 93-07
can be obtained by anonymous ftp (BINARY Mode) at
ftp.neuroinformatik.ruhr-uni-bochum.de
with path /pub/manuscripts/FuzzyRbfnES.ps.gz:
"Optimizing the Structure of Radial Basis Function Networks
by Optimizing Fuzzy Inference Systems with Evolution Strategy"
ABSTRACT
This report takes advantage of Neural Networks (NN) and
Fuzzy Inference Systems (FIS) in order to design a system suited to
predict time series.
We choose the solution of the Mackey--Glass time delay differential
equation in the chaotic domain as a sample problem.
Fuzzy rules are generated from the sample data.
The system performance is improved by means of Evolution Strategy (ES).
The rules of the FIS are diminished in number due to a heuristic
approach.
The optimization process is convenient for the structural design
of Radial Basis Function Networks (RBFN). The so far predetermined
RBFN is further optimized by gradient descent.
The system exhibits a good prediction accuracy and generalization.
Comments, suggestions, and questions are welcome.
If there are any problems with the gzip-format, the file may also
be transfered as an uncompressed text file just typing
ftp>get FuzzyRbfnES.ps
Regards,
Willfried Wienholt
ww@neuroinformatik.ruhr-uni-bochum.de
------------------------------
Subject: Proceedings available
From: Joan Cabestany <cabestan@eel.upc.es>
Date: Tue, 19 Oct 93 10:01:16 -0300
- ----------------------------- Start of body part 1
Please find herewith an announcement to be included in your distribution list.
For more details, feel free to contact me: cabestan@eel.up.es
Thanks
- ----------------------------- Start of body part 2
Proceedings available
_____________________
After the last edition of IWANN'93 (International Workshop on Artificial
Neural Networks) held in Spain (Sitges) during June 1993, some books with
the Proceedings are still available at special price.
Reference:
New Trends in Neural Computation (IWANN'93 Proceedings)
J.Mira, J.Cabestany, A.Prieto editors
Lecture Notes in Computer Science number 686
SPRINGER VERLAG 1993
Price: 9000 pesetas (spanish currency)
Method of payment:
VISA Card number _________________________ Expiration date _______________
Name of card holder ______________________________________________________
Date ____________ Signature ___________________________________
Send this form to
ULTRAMAR CONGRESS
Att. Mr. J.Balada
Diputacio, 238, 3
08007 BARCELONA Spain
Fax + 34.3.412.03.19
- ----------------------------- End of body part 2
------------------------------
Subject: Re: Where Can I Get Source for "NEURON"?
From: mukherj@rockyj.rockefeller.edu (Pratik Mukherjee)
Organization: Rockefeller University
Date: Thu, 23 Dec 93 05:38:26 -0500
In article <1993Dec21.140641.2522@ringer.cs.utsa.edu> senseman@lucy.brainlab.utsa.edu (David M. Senseman) writes:
>Could someone tell me how to get a hold of the modeling
>program "NEURON" that uses the GUI front-end built on
>the C++ library, "Interviews"? John Moore was demo'ing
>at Neuroscience and it looked very good.
>
>Thanks.
This program is available via anonymous ftp from neuron.neuro.duke.edu in
the directory /neuron/experimental-version.
>--
>David M. Senseman, Ph.D. | Imagine the Creator as a low
>(senseman@lucy.brainlab.utsa.edu) | comedian, and at once the world
>Life Sciences Visualization Lab | becomes explicable.
>University of Texas at San Antonio | H.L. Mencken
- Pratik Mukherjee
Laboratory of Biophysics
The Rockefeller University
mukherj@rockvax.rockefeller.edu
------------------------------
Subject: Submission to Neuron Request
From: 28-Dec-1993 0919 <pau@azur.enet.dec.com>
Date: Tue, 28 Dec 93 09:17:35 +0700
Please announce on the bulletin board :
Call for Submissions
Session on NEURAL NETWORKS and MACHINE LEARNING in
ECONOMICS and FINANCE
Amsterdam , Netherlands , 8-10 June 1994
during the IFAC/SEDC Intenational conference
"Computing in economics and finance" .
All research and applications papers are welcomed
related to neural networks,
machine learning,genetic algorithms and new approaches
to dynamic economic
processes.Authors wishing to contribute are invited to
submit a two-pages
long abstract by Feb 15,1994 to : L-F Pau, Digital
Equipment Europe,
POBox 27, F 06901 Sophia Antipolis,France.After
acceptance a full paper should
reach the conference organizers before May 01,1994 :
Prof Hans Amman,Dept. of
macroeconomics,University of Amsterdam,Roeterstraat
11,NL 1018 WB Amsterdam,
Netherlands.
------------------------------
Subject: MIT Press Book Announcement
From: Marilyn Geller <mgeller@MIT.EDU>
Date: Wed, 29 Dec 93 14:20:15 -0500
Just released by the MIT Press:
NEURAL NETWORK LEARNING AND EXPERT SYSTEMS
Stephen I. Gallant
NEURAL NETWORK LEARNING AND EXPERT SYSTEMS presents a unified and
in-depth development of neural network learning algorithms and neural
network expert systems. Especially suitable for students and researchers
in computer science, engineering, and psychology, it provides a
systematic development of neural network learning algorithms from a
computational perspective, coupled with an extensive exploration of
neural network expert systems which shows how the power of neural
network learning can be harnessed to generate expert systems
automatically.
Features include a comprehensive treatment of the standard learning
algorithms (with many proofs), along with much original research on
algorithms and expert systems. Additional chapters explore constructive
algorithms, introduce computational learning theory, and focus on expert
system applications to noisy and redundant problems.
For students there is a large collection of exercises, as well as a
series of programming projects that lead to an extensive neural network
software package. All of the neural network models examined can be
implemented using standard programming languages on a microcomputer.
Stephen I. Gallant taught courses in neural network learning and expert
systems as Associate Professor of Computer Science at Northeastern
University. He is currently a Senior Scientist at HNC, Inc.
A Bradford Book
March 1993 -- 364 pp. -- 156 illus. -- $42.50
ISBN 0-262-07145-2 GALNH
MIT Press books are available at bookstores or directly from the publisher.
For orders in the US
mitpress-orders@mit.edu
Call toll free: 1-800-356-0343 or (617) 625-8569. Or write The MIT Press
55 Hayward Street, Cambridge, MA 02142-1399, U.S.A.
When ordering, please specify this code: OML X35
For inquiries:
mitpress-order-inq@mit.edu
To access our catalogs telnet to: technifo.mit.edu and look under
\ Around MIT \ Offices and Services. This server is also a Gopher
server (gopher.mit.edu)
For price and order information in the UK, Eire and Continental Europe
please contact our London office at 14 Bloomsbury Square, London WC1A
2LP England, Tel (071) 404 0712 Fax (071) 404 0610 or via e-mail
100315.1423@compuserve.com
In Australia, please contact Astam Books, 57-61 John Street, Leichhardt,
NSW 2040 Australia Tel (02) 566 4400 Fax (02) 566 4411.
Please note that prices may be higher outside the US.
In all other areas or in case of difficulty, please contact The MIT
Press, International Department, 55 Hayward Street, Cambridge, MA 02142
USA Tel 617 253 2887 Fax 617 253 1709 or e-mail curtin@mit.edu
------------------------------
End of Neuron Digest [Volume 12 Issue 29]
*****************************************
