Copy Link
Add to Bookmark
Report
Machine Learning List Vol. 6 No. 18
Machine Learning List: Vol. 6 No. 18
Sunday, July 3, 1994
Contents:
ML/COLT tutorial -- Computational Learning Theory Intro & Survey
ML/COLT tutorial physics and learning
Tutorial notes available on LEARNING AND PROBABILITIES
COMPUTATIONAL LEARNING THEORY AND NATURAL LEARNING SYSTEMS
First UNIPEN Benchmark of On-line Handwriting Recognizers
CogSci-94 Technical Program and Schedule
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>
----------------------------------------------------------------------
Subject: ML/COLT tutorial -- Computational Learning Theory Intro & Survey
Date: Fri, 01 Jul 94 15:21:49 EDT
From: Lenny Pitt <pitt@cs.uiuc.edu>
=========================================================
Computational Learing Theory: Introduction and Survey
=========================================================
Sunday, July 10, 1994
8:45 am to 12:15 pm
Rutgers University
New Brunswick, New Jersey
Tutorial conducted by
Lenny Pitt
University of Illinois
Urbana, IL 61801
pitt@cs.uiuc.edu
Held in conjunction with the Eleventh International
Conference on Machine Learning (ML94, July 11-13, 1994)
and the Seventh Annual Conference on Computational
Learning Theory (COLT94, July 12-15, 1994).
This tutorial will introduce the different formal learning models
(eg, ``pac'' learning, mistake-bounded learning, learning with queries),
present basic techniques for proving learnability and nonlearnability
(eg, the VC-dimension, Occam algorithms, reductions between learning problems),
and survey many of the central results in the area.
The tutorial is designed to give ML attendees and those with a general interest
in machine learning sufficient background to appreciate past and recent
results in computational learning theory. It should also help attendees
appreciate the significance and contributions of the papers that will be
presented at the COLT94 conference that follows. No prior knowledge of
learning theory is assumed.
The tutorial is one of a set of DIMACS-sponsored tutorials that
are free and open to the general public.
Directions to Rutgers can be found in the ML/COLT announcement,
which is available via anonymous ftp from www.cs.rutgers.edu in
the directory "/pub/learning94". The specific location of the
tutorial will be posted, and available with conference materials.
Users of www information servers such as mosaic can find the information at
"http://www.cs.rutgers.edu/pub/learning94/learning94.html".
Other available information includes a campus map, and abstracts of all
workshops/tutorials. Questions can be directed to ml94@cs.rutgers.edu,
or to colt94@research.att.com.
------------------------------
From: seung@physics.att.com
Date: Thu, 30 Jun 94 17:20:15 EDT
Subject: tutorial announcement--statistical physics and learning
=========================================================
What does statistical physics have to say about learning?
=========================================================
Sunday, July 10, 1994
8:45 am to 12:15 pm
Milledoler Hall, room 100
Rutgers University
New Brunswick, New Jersey
Tutorial conducted by
Sebastian Seung and Michael Kearns
AT&T Bell Laboratories
Murray Hill, NJ 07974
Free of charge and open to the general public,
thanks to sponsorship from DIMACS.
Held in conjunction with the Eleventh International
Conference on Machine Learning (ML94, July 11-13, 1994)
and the Seventh Annual Conference on Computational
Learning Theory (COLT94, July 12-15, 1994).
The study of learning has historically been the domain of
psychologists, statisticians, and computer scientists. Statistical
physicists are the seemingly unlikely latecomers to the subject. This
tutorial is an overview of the ideas they are now bringing to learning
theory, and of the relationship of these ideas to statistics and
computational learning theory. We focus on the analysis of learning
curves, defined here as graphs of generalization error versus the
number of examples used in training. We explain why supervised
learning from examples can lead to learning curves with a variety of
behaviors, some of which are very different from (though consistent
with) the Vapnik-Chervonenkis bounds. This is illustrated most
dramatically by the presence of phase transitions in certain learning
models. We discuss theoretical progress towards understanding two
puzzling empirical findings--that neural networks sometimes attain
good generalization with fewer examples than adjustable parameters,
and that generalization performance can be relatively insensitive to
the size of the hidden layer. We conclude with a discussion of the
relationship of the statistical physics approach with that of the
Vapnik-Chervonenkis theory.
No prior knowledge of learning theory will be assumed. This tutorial
is one of a set of DIMACS-sponsored tutorials that are free and open
to the general public. Directions to Rutgers can be found in the
ML/COLT announcement, which is available via anonymous ftp from
www.cs.rutgers.edu in the directory "/pub/learning94". Users of www
information servers such as mosaic can find the information at
"http://www.cs.rutgers.edu/pub/learning94/learning94.html". Other
available information includes a campus map, and abstracts of all
workshops/tutorials. Questions can be directed to
ml94@cs.rutgers.edu, colt94@research.att.com, or to Sebastian Seung at
908-582-7418 and seung@physics.att.com
------------------------------
Date: Thu, 30 Jun 94 11:59:50 PDT
From: Wray Buntine <wray@ptolemy-ethernet.arc.nasa.gov>
Subject: Tutorial notes available on LEARNING AND PROBABILITIES
LEARNING AND PROBABILITIES
**************************
(For MLnet Summer School on Machine Learning and Knowledge Acquisition,
Paris, 5th-10th September, 1994))
Wray Buntine, RIACS
NASA Ames Research Center, MS 269-2
Moffet Field, CA 94035-1000
wray@kronos.arc.nasa.gov
(C) Copyright, June, 1994, Wray Buntine.
Thanks to Padhraic Smyth and Peter Cheeseman for input.
Approx. 3 hours. Not all slides will be covered in the presentation.
Abstract:
+++++++++
Probabilistic methods offer general tools and theory for the design of
learning algorithms. This tutorial introduces some basic issues in learning
and then introduces basic principles of probability as they apply to
learning. Second, probabilistic graphical models are being used widely in
artificial intelligence in, for instance, diagnosis and expert systems. This
tutorial also explains how these models can be extended to machine learning,
neural networks, knowledge discovery, and knowledge refinement. This offers
a technology for developing a learning tool-box, whereby by a learning or
discovery system can be compiled according to probabilistic principles from
a graphical specification.
An extensive bibliography is included.
Compressed Postscript for this tutorial is available (500Kb) at:
URL = ftp://riacs.edu/pub/Wray/MLNet.ps.Z
FTP site = riacs.edu
FTP file = pub/Wray/MLNet.ps.Z
o OVERVIEW OF TUTORIAL
o SECTION Ia.
o LEARNING
o ON THE DESIGN OF ALGORITHMS
o EXAMPLE DESIGNS
o DESIGN COMPONENTS
o BAYESIAN THEORY: ASIDE
o BASIC CONTEXT FOR DATA ANALYSIS
o BASIC SOFTWARE GENERATOR
o ADVANTAGES OF SOFTWARE GENERATORS
o SECTION Ib.
o BACKGROUND OF EARLY STATISTICS
o THE TURNING POINT OF STATISTICS (1940-60s): LEARNING?
HOW?
o MODERN LEARNING METHODS: FILLING THE VACUUM
o MORE MODERN LEARNING METHODS: FILLING THE
VACUUM
o LEARNING THEORIES AND METHODS: SUMMARY
o SECTION IIa.
o LEARNING CURVES
o SUBSECTION: BASIC ISSUES IN LEARNING
o EXAMPLE: SMOOTHING & OVERFITTING
o SMOOTHING, cont.
o EXAMPLE: LESS SMOOTHING
o EXAMPLE: MODEL UNCERTAINTY
o MODEL UNCERTAINTY, cont.
o EXAMPLE: MULTIPLE MODELS
o EXAMPLE: YOU HAVE INFINITE DATA!
o EXAMPLE: BIAS VERSUS VARIANCE
o BIAS VERSUS VARIANCE, cont.
o OBJECTIVITY vs. SUBJECTIVITY
o SUMMARY OF LESSONS
o QUESTIONS FOR A THEORY OF LEARNING
o SECTION IIb.
o EXAMPLE, BERNOULLI
o EXAMPLE, BERNOULLI
o EXAMPLE, BERNOULLI, continued
o EXAMPLE, BERNOULLI, continued
o EXAMPLE, BERNOULLI, continued
o DECISION STUMPS AND BAYES NETS
o LEARNING DECISION STUMPS, cont.
o LEARNING DECISION STUMPS, cont.
o LEARNING DECISION STUMPS, cont.
o LEARNING DECISION STUMPS, cont.
o LEARNING DECISION STUMPS, cont.
o LEARNING DECISION STUMPS, cont.
o SUMMARY OUTLINE: BELIEF
o SUMMARY OUTLINE: ACTIONS
o SECTION IIIa.
o AN IMAGE PROBLEM
o THE IMAGE MODEL
o ON MODELS
o INTRODUCTION TO BAYESIAN NETS
o INTRODUCTION TO BAYESIAN NETWORKS, cont
o THE BAYESIAN NETWORK FOR AUTOCLASS III
o LEGEND FOR GRAPHICAL MODELS
o UNSUPERVISED LEARNING FOR IMAGES
o FEED-FORWARD NETWORKS (FFNNS)
o GRAPHICAL MODELS
o GRAPHICAL MODELS, cont.
o SECTION IIIb.
o MIXTURE MODELS: EXAMPLE
o MIXTURE MODELS: EXAMPLE, cont.
o MIXTURE MODELS: MOTIVATION
o MIXTURE MODELS
o ALGORITHMS ON MIXTURES
o K-MEANS ALGORITHM
o K-MEANS ALGORITHM: ANALYSIS
o GRAPHICAL MODEL
o EM ALGORITHM
o EM ALGORITHM: ANALYSIS
o GIBBS ALGORITHM
o GIBBS ALGORITHM: INTERPRETATION
o GIBBS ALGORITHM: ANALYSIS
o K-MEANS vs. EM vs. GIBBS
o SECTION VIa.
o MISSING VALUES
o OTHER TYPES OF MISSING VALUES
o BASIC OUTLINE OF MISSING VALUES
o MISSING VALUES IN DISCRIMINATIVE LEARNING
o EXAMPLE: DISCRIMINATIVE METHODS
o MISSING VALUES IN GENERATIVE LEARNING
o EXAMPLE: GENERATIVE METHODS
o METHODS: IGNORE THEM
o DISCRIMINATIVE METHODS: FILL-IN
o GENERATIVE METHODS: FILL-IN
o METHODS: FRACTIONAL EXAMPLES
o OTHER METHODS
o SECTION VIb.
o HYBRID CLUSTERING AND KNOWLEDGE DISCOVERY
o KNOWLEDGE REFINEMENT
o UNSUPERVISED LEARNING: STYLES
o KNOWLEDGE REFINEMENT/DISCOVERY CYCLE
o SECTION VIc.
o LEARNING BAYESIAN NETWORKS
o PAC THEORY
o WHAT DOES PAC CONFIDENCE MEAN?
o APPROXIMATE BAYESIAN THEORY
o MDL THEORY
o STATISTICAL PHYSICS APPLIED TO PERCEPTRONS
o PERCEPTRONS, cont.
o LEARNING THEORIES: SUMMARY
o SECTION VII.
o CHECK LIST OF REPRESENTATIONS
o CHECK LIST OF METHODS
o CHECK LIST OF THEORY
o NEW ALGORITHMS FROM OLD
o SOME RESEARCH QUESTIONS
o References
Wray Buntine
NASA Ames Research Center phone: (415) 604 3389
Mail Stop 269-2 fax: (415) 604 3594
Moffett Field, CA, 94035-1000 email: wray@kronos.arc.nasa.gov
------------------------------
Date: Wed, 29 Jun 1994 14:37:06 -0400
From: Thomas Petsche <petsche@scr.siemens.com>
Subject: COMPUTATIONAL LEARNING THEORY AND NATURAL LEARNING SYSTEMS
The following book is now available from MIT Press:
COMPUTATIONAL LEARNING THEORY AND NATURAL LEARNING SYSTEMS
Volume II: Intersection between Theory and Experiments
Edited by Stephen J. Hanson, Thomas Petsche, Michael Kearns, and
Ronald L. Rivest.
The book is the result of a workshop of the same name which brought
together researchers from learning theory, machines learning, and
neural networks. The book includes 23 chapters by authors in these
various fields plus a unified bibliography and index:
1. Bayes Decisions in a Neural Network-PAC Setting
Svetlana Anulova, Jorge R. Cuellar, Klaus-U. Hoeffgen and Hans-U. Simon
2. Average Case Analysis of $k$-CNF and $k$-DNF Learning Algorithms
Daniel S. Hirschberg, Michael J. Pazzani and Kamal M. Ali
3. Filter Likelihoods and Exhaustive Learning
David H. Wolpert
4. Incorporating Prior Knowledge into Networks of Locally-Tuned Units
Martin Roescheisen, Reimar Hofmann and Volker Tresp
5. Using Knowledge-Based Neural Networks to Refine Roughly-Correct
Information
Geoffrey G. Towell and Jude W. Shavlik
6. Sensitivity Constraints in Learning
Scott H. Clearwater and Yongwon Lee
7. Evaluation of Learning Biases Using Probabilistic Domain Knowledge
Marie desJardins
8. Detecting Structure in Small Datasets by Network Fitting under
Complexity Constraints
W. Finnoff and H.G. Zimmermann
9. Associative Methods in Reinforcement Learning: An Empirical Study
Leslie Pack Kaelbling
10. A Schema for Using Multiple Knowledge
Matjaz Gams, Marko Bohanec and Bojan Cestnik
11. Probabilistic Hill-Climbing
William W. Cohen, Russell Greiner and Dale Schuurmans
12. Prototype Selection Using Competitive Learning
Michael Lemmon
13. Learning with Instance-Based Encodings
Henry Tirri
14. Contrastive Learning with Graded Random Networks
Javier R. Movellan and James L. McClelland
15. Probability Density Estimation and Local Basis Function Neural Networks
Padhraic Smyth
16. Hamiltonian Dynamics of Neural Networks
Ulrich Ramacher
17. Learning Properties of Multi-Layer Perceptrons with and without
Feedback
D. Gawronska, B. Schuermann and J. Hollatz
18. Unsupervised Learning for Mobile Robot Navigation Using
Probabilistic Data Association
Ingemar J. Cox and John J. Leonard
19. Evolution of a Subsumption Architecture that Performs a Wall
Following Task for an Autonomous Mobile Robot
John R. Koza
20. A Connectionist Model of the Learning of Personal Pronouns in
English
Thomas R. Shultz, David Buckingham and Yuriko Oshima-Takane
21. Neural Network Modeling of Physiological Processes
Volker Tresp, John Moody and Wolf-Ruediger Delong
22. Projection Pursuit Learning: Some Theoretical Issues
Ying Zhao and Christopher G. Atkeson
23. A Comparative Study of the Kohonen Self-Organizing Map and the
Elastic Net
Yiu-fai Wong
The book is ISBN 0-262-58133-7 and the price is $35 (I believe).
Additional ordering information can be obtained from:
Neil Blaisdell
MIT/Bradford Books
Sales Department
blaisdel@mit.edu
(They will take a credit card order if you like (and trust the
net with you credit card number).)
------------------------------
Subject:First UNIPEN Benchmark of On-line Handwriting Recognizers
Date: Mon, 27 Jun 94 19:21:23 EDT
From: Isabelle Guyon <isabelle@neural.att.com>
> - > - > - > - > - > - > - > - < - < - < - < - < - < - < - < - < -
- > First UNIPEN Benchmark of On-line Handwriting Recognizers < -
-> Organized by NIST < -
- > - > - > - > - > - > - > - > - < - < - < - < - < - < - < - < - < -
June 1994
* CALL FOR DATA (please post)
At the initiative of Technical Committee 11 of the International Association
for Pattern Recognition (IAPR), the UNIPEN project was started to
stimulate research and development in on-line handwriting recognition
(e. g. for pen computers and pen communicators). UNIPEN provides a platform of
data exchange at the Linguistic Data Consortium (LDC) and is organizing
this year a worldwide benchmark under the control of the US National Institute
of Standards and Technologies (NIST). The benchmark is concerned with writer
independent recognition of sentences, isolated words and isolated characters of
any writing style (handprinted and/or cursive). Although UNIPEN will provide,
in the future, data for various alphabets, this particular benchmark is
limited to letters and symbols from an English computer keyboard . The data
will be donated by the participants.
* Conditions of participation
Participation to the benchmark is open to any individual or institution who
provides a sample of handwriting in the UNIPEN format which contains at least
12,000 characters. The data must be of acceptable quality and donated by
October 1st, 1994 . The database of donated samples will be available for free
to the data donators. Registration material can be obtained by sending email
to Stan Janet at stan@magi.ncsl.nist.gov or via ftp:
ftp ftp.cis.upenn.edu
Name: anonymous
Password: [use your email address]
ftp> cd pub/UNIPEN-pub/documents
ftp> get call-for-data.ps
ftp> quit
* Organizing committee
Isabelle Guyon, AT&T Bell Laboratories, USA
Lambert Schomaker, Nijmegen Institute for Cognition and Information, The Netherlands
Stan Janet, National Institute of Standards and Technologies, USA
Mark Liberman, Linguistic Data Consortium, University of Pennsylvania, USA
Rejean Plamondon, IAPR, TC11, Ecole Polytechnique de Montreal, Canada
------------------------------
Date: Fri, 24 Jun 1994 16:23:33 -0400
From: Ashwin Ram <ashwin@cc.gatech.edu>
Subject: CogSci-94 Technical Program and Schedule
Here is the technical program and schedule for the Sixteenth Annual
Conference of the Cognitive Science Society (CogSci-94). This program is
available on the World Wide Web at http://www.gatech.edu/cogsci/cogsci.html
and by anonymous FTP from ftp.cc.gatech.edu:/pub/cogsci94. These sites also
contain other CogSci-94 information, including registration forms, travel and
hotel information, and a searchable index of the titles, authors, and
abstracts of all the papers to be presented at the conference. (For example,
ML folks might want to search for keywords such as "learning",
"categorization", "analogy", etc., to dig up all papers relevant to these
topics.) For further information, e-mail cogsci94@cc.gatech.edu.
Sat Aug 13 Sun Aug 14 Mon Aug 15 Tue Aug 16 Wed Aug 17
9-10:30 Plenary Plenary Plenary All-day
11-12:30 Parallel Parallel Parallel education
workshop
2-3:30 Parallel Parallel Plenary Panel
4-5:30 Parallel Parallel
night Keynote Banquet Posters
+Reception +Reception
NOTE: Each "parallel" session consists of:
a symposium
two paper sessions
a poster+discussant session
==============================================================================
Sat Aug 13 Sun Aug 14 Mon Aug 15 Tue Aug 16
9-10:30 Plenary: Plenary: Plenary:
GLEITMAN SCHNEIDER PAZZANI
10:30-11 Break Break Break
11-12:30 Symposium: Symposium: Symposium:
SCIENTIFIC COG SCI MEETS COLLABORATIVE
CREATIVITY COG ENGG KNOWLEDGE
Paper: Paper: Paper:
CATEGORIZATION ANALOGICAL LEARNING
REASONING
Paper: Paper: Paper:
REASONING SENTENCE BELIEF
PROCESSING MODELING
Poster+Discuss: Poster+Discuss: Poster+Discuss:
SPEECH PERCEPTION SYNTACTIC
PROCESSING
12:30-2 Lunch Lunch Lunch
2-3:30 Symposium: Symposium: Plenary Panel:
ANIMAL VISUAL COGSCI 2004 --
COGNITION REASONING THE LAST 10 YEARS
Paper: Paper:
COLLABORATIVE PROBLEM
PROB SOLV SOLVING
Paper: Paper:
REPRESENTATION BRAIN
IN CONN NETS MODELING
Poster+Discuss: Poster+Discuss:
ANALOGY LEARNING
3:30-4 Break Break
4-5:30 Symposium: Symposium:
LEARNING ROLE OF CASES
NEW FEATURES IN LEARNING
Paper: Paper:
SITUATED VISUAL
NAT LANG PERCEPTION
Paper: Paper:
FOUNDATIONS MENTAL
MODELS
Poster+Discuss: Poster+Discuss:
VISUAL LANGUAGE
REASONING ACQUISITION
5-6:30 Reception
6:30-8 Keynote: Gala Banquet Poster
WOODS Presentations
==============================================================================
Saturday, August 13, 1994
5:00pm-6:30pm
Welcoming Reception
6:30pm-8:00pm
Keynote Speaker: David Woods
"Observations from Studying Cognitive Systems in Context"
Sunday, August 14, 1994
9:00am-10:30am
Plenary Speaker: Lila Gleitman
"A Picture Is Worth a Thousand Words -- But That's the Problem"
10:30am-11:00am
Break
11:00am-12:30pm
Symposium
"Scientific Creativity: Multidisciplinary Perspectives"
N.J. Nersessian, Chair; J. Clement, K. Dunbar, R. Jones, R. Tweney
11:00am-12:30pm
Paper Presentations
Topic: Categorization
"Functional and Conditional Equivalence: Conceptual Contributions From Behavior Analysis"
A. Cabrera
"Categorization and the Parsing of Objects"
R. Pevtzow and R.L. Goldstone
"Categorization, Typicality, and Shape Similarity"
M.A. Kurbat, E.E. Smith, and D.L. Medin
"Learning of Rules That Have High-Frequency Exceptions: New Empirical Data and a Hybrid Connectionist Model"
J.K. Kruschke and M.A. Erickson
"Modeling Inter-Category Typicality Within a Symbolic Search Framework"
C.S. Miller
11:00am-12:30pm
Paper Presentations
Topic: Reasoning
"Counterfactual Reasoning: Inferences From Hypothetical Conditionals"
R.M.J. Byrne and A. Tasso
"How Mathematicians Prove Theorems"
E. Melis
"The Implications of Corrections: Then Why Did You Mention It?"
J.G. Bush, H.M. Johnson, and C.M. Seifert
"The Power of Negative Thinking: The Central Role of Modus Tollens in Human Cognition"
S. Ohlsson and N. Robin
"Toward a Theoretical Account of Strategy Use and Sense-Making in Mathematics Problem Solving"
H.J.M. Tabachneck, K.R. Koedinger, and M.J. Nathan
11:00am-12:30pm
Poster Presentations with Discussant
Topic: Speech
"On-Line Versus Off-Line Priming of Word-Form Encoding in Spoken Word Production"
A. Roelofs
"Towards a New Model of Phonological Encoding"
P.J.A. Meijer
"Acoustic-Based Syllabic Representation and Articulatory Gesture Detection: Prerequisites for Early Childhood Phonetic and Articulatory Development"
K.L. Markey
"Modelling Retroactive Context Effects in Spoken Word Recognition With a Simple Recurrent Network"
A. Content and P. Sternon
"Using Connectionist Networks to Examine the Role of Prior Constraints in Human Learning"
M. Harm, L. Altmann, and M.S. Seidenberg
"Distribution and Frequency: Modelling the Effects of Speaking Rate on Category Boundaries Using a Recurrent Neural Network"
M. Abu-Bakar and N. Chater
"Inference Processes in Speech Perception"
G. Gaskell and W. Marslen-Wilson
12:30pm-2:00pm
Lunch
2:00pm-3:30pm
Symposium
"What Animal Cognition Tells Us About Human Cognition"
A. Francis, Chair; D. Rumbaugh, M. Tomasello
2:00pm-3:30pm
Paper Presentations
Topic: Collaborative Problem Solving
"Effects of Collaborative Interaction and Computer Tool Use"
S. Derry and K. Tookey
"Managing Disagreement in Intellectual Conversations: Coordinating Interpersonal and Conceptual Concerns in the Collaborative Construction of Mathematical Explanations"
R.A. Engle and J.G. Greeno
"Rational Choice and Framing Devices: Argumentation and Computer Programming"
S. Coulson and N.V. Flor
"Distributed Meeting Scheduling"
J. Liu and K.P. Sycara
"Handling Unanticipated Events During Collaboration"
R.M. Turner and P.S. Eaton
2:00pm-3:30pm
Paper Presentations
Topic: Representation in Connectionist Networks
"The Null List Strength Effect in Recognition Memory: Environmental Statistics and Connectionist Accounts"
S. Dennis
"Strong Systematicity Within Connectionism: The Tensor-Recurrent Network"
S. Phillips
"Can Connectionist Models Exhibit Non-Classical Structure Sensitivity?"
L. Niklaisson and T. van Gelder
"Dynamically Constraining Connectionist Networks to Produce Distributed, Orthogonal Representations to Reduce Catastrophic Interference"
R.M. French
"Synchronous Firing Variable Binding is a Tensor Product Representation With Temporal Role Vectors"
B.B. Tesar and P. Smolensky
2:00pm-3:30pm
Poster Presentations with Discussant
Topic: Analogy
"Adaptation as a Selection Constraint on Analogical Mapping"
M.T. Keane
"Similarity by Feature Creation: Reexamination of the Asymmetry of Similarity"
H. Ohnishi, H. Suzuki, and K. Shigemasu
"Mapping Hierarchical Structures With Synchrony for Binding: Preliminary Investigations"
J.E. Hummel, E.R. Melz, J. Thompson, and K.J. Holyoak
"Analogical Transfer Through Comprehension and Priming"
C.M. Wharton and T.E. Lange
"Competing Models of Analogy: ACME Versus Copycat"
B.D. Burns and K.J. Holyoak
"Simulating Similarity-Based Retrieval: A Comparison of ARCS and MAC/FAC"
K. Law, K.D. Forbus, and D. Gentner
"MAGI: Analogy-Based Encoding Using Regularity and Symmetry"
R.W. Ferguson
3:30pm-4:00pm
Break
4:00pm-5:30pm
Symposium
"Learning New Features of Representation"
R. Goldstone and P. Schyns, Chairs; B. French, D.L. Medin, M. Mozer, J.-P. Thibaut
4:00pm-5:30pm
Paper Presentations
Topic: Situated Natural Language
"A Taxonomy for Planned Reading"
T. Carpenter and R. Alterman
"Integrating Creativity and Reading: A Functional Approach"
K. Moorman and A. Ram
"KA: Situating Natural Language Understanding in Design Problem Solving"
J. Peterson, K. Mahesh, A. Goel, and K. Eiselt
"Modeling the Interaction Between Speech and Gesture"
J. Cassell, M. Stone, B. Douville, S. Prevost, B. Achorn,
M. Steedman, N. Badler, and C. Pelachaud
"Integrating Cognitive Capabilities in a Real-Time Task"
G. Nelson, J.F. Lehman, and B.E. John
4:00pm-5:30pm
Paper Presentations
Topic: Foundations
"Formal Rationality and Limited Agents"
J.K. Tash
"Integrating, Not Debating, Situated Action and Computational Models: Taking the Environment Seriously"
M.D. Byrne
"Classicalism and Cognitive Architecture"
T. van Gelder and L. Niklasson
"On the Psychological Basis for Rigid Designation"
N. Braisby, B. Franks, and J. Hampton
"Situated Cognition: Empirical Issue, `Paradigm Shift' or Conceptual Confusion?
P. Slezak
4:00pm-5:30pm
Poster Presentations with Discussant
Topic: Visual Reasoning
"An Empirical Investigation of Law Encoding Diagrams for Instruction"
P.C-H. Cheng
"Graphical Effects in Learning Logic: Reasoning, Representation and Individual Differences"
R. Cox, K. Stenning, and J. Oberlander
"Understanding Diagrammatic Demonstrations"
R.K. Lindsay
"Scaffolding Effective Problem Solving Strategies in Interactive Learning Environments"
D.C. Merrill and B.J. Reiser
"How Graphs Mediate Analog and Symbolic Representation"
M. Gattis and K.J. Holyoak
"How Does and Expert Use a Graph? A Model of Visual and Verbal Inferencing in Economics"
H.J.M. Tabachneck, K.R. Koedinger, and H.A. Simon
"A Study of Diagrammatic Reasoning From Verbal and Gestural Data"
N.H. Narayanan, M. Suwa, and H. Motoda
"Imagistic Simulation and Physical Intuition in Expert Problem Solving"
J. Clement
6:30pm-8:00pm
Gala Banquet
Monday, August 15, 1994
9:00am-10:30am
Plenary Speaker: Walter Schneider
"Identifying the Modules of the Mind with fMRI: Imaging the Biological Stages in Visual and Language Processing"
10:30am-11:00am
Break
11:00am-12:30pm
Symposium
"Cognitive Science Meets Cognitive Engineering"
R. Catrambone, Chair; S.T. Dumais, J. Elkerton, B.E. John, M.G. Shafto
11:00am-12:30pm
Paper Presentations
Topic: Analogical Reasoning
"Commonsense Knowledge and Conceptual Structure in Container Metaphors"
T.C. Clausner
"Case Age: Selecting the Best Exemplars for Plausible Reasoning Using Distance in Time or Space"
M.H. Burstein
"The Effect of Similarity on Memory for Prior Problems"
J.M. Faries and K.R. Schlossberg
"The Coherence Imbalance Hypothesis: A Functional Approach to Asymmetry in Comparison"
D. Gentner and B.F. Bowdle
"Incremental Structure-Mapping"
K.D. Forbus, R.W. Ferguson, and D. Gentner
11:00am-12:30pm
Paper Presentations
Topic: Sentence Processing
"The Construction-Integration Model: A Framework for Studying Context Effects in Sentence Processing"
E.C. Ferstl
"A Unified Model of Preference and Recovery Mechanisms in Human Parsing"
S. Stevenson
"Uniform Representations for Syntax-Semantics Arbitration"
K. Mahesh and K.P. Eiselt
"Lexical Disambiguation Based on Distributed Representations of Context Frequency"
M.R. Mayberry III and R. Miikkulainen
"Multiple Constraints in Syntactic Ambiguity Resolution: A Connectionist Account of Psycholinguistic Data"
C. Burgess and K. Lund
11:00am-12:30pm
Poster Presentations with Discussant
Topic: Perception
"Simulated Perceptual Grouping: An Application to Human-Computer Interaction"
K.R. Thorisson
"Using Trajectory Mapping to Analyze Musical Intervals"
S.A. Gilbert and W. Richards
"Functional Parts"
J. Tenenbaum
"Letter Perception: Toward a Conceptual Approach"
G. McGraw, J. Rehling, and R. Goldstone
"Viewpoint Dependence and Face Recognition"
P.G. Schyns and H.H. Bulthoff
"A Connectionist Account of Global Precedence: Theory and Data"
E.M. Olds
"Time as Phase: A Dynamic Model of Time Perception"
J.D. McAuley
"Models of Metrical Structure in Music"
E.W. Large
12:30pm-2:00pm
Lunch
2:00pm-3:30pm
Symposium
"Visual Reasoning in Discovery, Instruction, and Problem Solving"
N.H. Narayanan, Chair; M. Hegarty, R. Hall, N. Nersessian
2:00pm-3:30pm
Paper Presentations
Topic: Problem Solving
"Causal Attribution as Mechanism-Based Story Construction: An Explanation of the Conjunction Fallacy and the Discounting Principle"
W. Ahn, J. Bailenson, and B. Gordon
"Troubleshooting Strategies in a Complex, Dynamical Domain"
M.M. Recker, T. Govindaraj, and V. Vasandani
"The Effects of Labels in Examples on Problem Solving Transfer"
R. Catrambone
"Goal Specificity in Hypothesis Testing and Problem Solving"
R. Vollmeyer, K.J. Holyoak, and B.D. Burns
"Problem Content Affects the Categorization and Solutions of Problems"
S.B. Blessing and B.H. Ross
2:00pm-3:30pm
Paper Presentations
Topic: Brain Modeling
"Binding of Object Representations by Synchronous Cortical Dynamics Explains Temporal Order and Spatial Pooling Data"
A. Grunewald and S. Grossberg
"Computing Goal Locations From Place Codes"
H.S. Wan, D.S. Touretzky, and A.D. Redish
"Connectionist Modelling of Spelling"
J.A. Bullinaria
2:00pm-3:30pm
Poster Presentations with Discussant
Topic: Learning
"Changing the Viewpoint: Re-Indexing by Introspective Questioning"
R. Oehlmann, P. Edwards, and D. Sleeman
PCLEARN: A Model for Learning Perceptual-Chunks"
M. Suwa and H. Motoda
"Multiple Learning Mechanisms Within Implicit Learning"
C.A. Seger
"Direct and Indirect Measures of Implicit Learning"
L. Jimenez and A. Cleeremans
"Failure-Driven Learning as Input Bias"
M.T. Cox and A. Ram
"Using Introspective Reasoning to Guide Index Refinement in Case-Based Reasoning"
S. Fox and D. Leake
"An Experiment to Determine Improvements in Automated Problem Solving in a Complex Problem Domain"
M. Van Dyne and C. Tsatsoulis
"Abstraction of Sensory-Motor Features"
K. Hiraki
3:30pm-4:00pm
Break
4:00pm-5:30pm
Symposium
"The Role of Cases in Learning"
T. Koschmann, Chair; A. Collins, K. Holyoak, G. Klein, J.L. Kolodner
4:00pm-5:30pm
Paper Presentations
Topic: Visual Perception
"Attention Allocation During Movement Preparation"
M.H. Fischer
"How Do Representations of Visual Form Organize Our Percepts of Visual Motion?"
G. Francis and S. Grossberg
"The Curtate Cycloid Illusion: Cognitive Constraints on the Processing of Rolling Motion"
M.I. Isaak and M.A. Just
"A Simple Co-Occurrence Explanation for the Development of Abstract Letter Identities"
T.A. Polk and M.J. Farah
"Computational Simulation of Depth Perception in the Mammalian Visual System"
J.S. Jin
4:00pm-5:30pm
Paper Presentations
Topic: Mental Models
"Array Representations for Model-Based Spatial Reasoning"
J. Glasgow
"Mental Models in Propositional Reasoning"
B.G. Bara, M. Bucciarelli, P.N. Johnson-Laird, and V. Lombardo
"Do Children Have Epistemic Constructs About Explanatory Frameworks: Examples From Naive Ideas About the Origin of Species"
A. Samarapungavan and R. Wiers
"When `Or' Means `And': A Study in Mental Models"
P.N. Johnson-Laird and P.E. Barres
"Mental Models for Proportional Reasoning"
J.L. Moore and D.L. Schwartz
4:00pm-5:30pm
Poster Presentations with Discussant
Topic: Language Acquisition
"A Lexical Model of Learning to Read Single Words Aloud"
R. Taraban and C.B. Taraban
"Predicting Irregular Past Tenses: Comparing Symbolic and Connectionist Models Against Native English Speakers"
C.X. Ling
"Correspondences Between Syntactic Form and Meaning: From Anarchy to Hierarchy"
J. Peterson and D. Billman
"Artificial Evolution of Syntactic Aptitude"
J. Batali
"Distributional Bootstrapping: From Word Class to Proto-Sentence"
S. Finch and N. Chater
"Are Children `Lazy Learners'? A Comparison of Natural and Machine Learning of Stress"
S. Gillis, W. Daelemans, and G. Durieux
"Objects, Actions, Nouns, and Verbs"
P.M. Hastings and S.L. Lytinen
"Levels of Semantic Constraint and Learning Novel Words"
J.M. Lampinen and J.M. Faries
"Segmenting Speech Without a Lexicon: Evidence for a Bootstrapping Model of Lexical Acquisition"
T.A. Cartwright and M.R. Brent
"Verb Inflections in German Child Language: A Connectionist Account"
G. Westermann and R. Miikkulainen
6:30pm-8:00pm
Poster Presentations
"Interactive Model-Driven Case Adaptation for Instructional Software Design"
B. Bell, S. Kedar, and R. Bareiss
"The Theory-Ladenness of Data: An Experimental Demonstration"
W.F. Brewer and C.A. Chinn
"Kant and Cognitive Science"
A. Brook
"A Connectionist Model of the Development of Velocity, Time, and Distance Concepts"
D. Buckingham and T.R. Shultz
"Internal Representations of a Connectionist Model of Reading Aloud"
J.A. Bullinaria
"Lexical Segmentation: The Role of Sequential Statistics in Supervised and Un-Supervised Models"
P. Cairns, R. Shillcock, N. Chater, and J. Levy
"Are Scientific Theories That Predict Data More Believable Than Theories That Retrospectively Explain Data? A Psychological Investigation"
C.A. Chinn
"The Architecture of Intuition: Converging Views From Physics Education and Linguistics"
M.M. Chiu and J. Gutwill
"A Descriptive Model of Question Asking During Story Acquisition Interviews"
C. Cleary and R. Bareiss
"Individual Differences and Predictive Validity in Student Modeling"
A.T. Corbett, J.R. Anderson, V.H. Carver, and S.A. Brancolini
"Natural Oculomotor Performance in Looking and Tapping Tasks"
J. Epelboim, H. Collewijn, E. Kowler, C.J. Erkelens, M. Edwards, Z. Pizlo, and R.M. Steinman
"Learning the Arabic Plural: The Case for Minority Default Mappings in Connectionist Networks"
N. Forrester and K. Plunkett
"Scientific Discovery in a Space of Structural Models: An Example From the History of Solution Chemistry"
A. Gordon, P. Edwards, D. Sleeman, and Y. Kodratoff
"Psychological Evidence for Assumptions of Path-Based Inheritance Reasoning"
C. Hewson and C. Vogel
"WanderECHO: A Connectionist Simulation of Limited Coherence"
C.M. Hoadley, M. Ranney, and P. Schank
"PROVERB - A System Explaining Machine-Found Proofs"
X. Huang
"Suppression of Misinformation in Memory"
H.M. Johnson and C.M. Seifert
"A Computational Model of Human Abductive Skill and its Acquisition"
T.R. Johnson, J. Krems, and N.K. Amra
"Bottom-Up Recognition Learning: A Compilation-Based Model of Limited-Lookahead Learning"
T.R. Johnson, J. Zhang, and H. Wang
"Adaptive Learning of Gaussian Categories Leads to Decision Bounds and Response Surfaces Incompatible with Optimal Decision Making"
M. Kalish
"Coping With the Complexity of Design: Avoiding Conflicts and Prioritizing Constraints"
I.R. Katz
"Semantics and Pragmatics of Vague Probability Expressions"
B. Kipper and A. Jameson
"The Context-Sensitive Cognitive Architecture DUAL"
B.N. Kokinov
"The Origin of Clusters in Recurrent Neural Network State Space"
J.F. Kolen
"Recurrent Natural Language Parsing"
S.C. Kwasny, S. Johnson, and B.L. Kalman
"Error Modeling in the ACT-R Production System"
C. Lebiere, J.R. Anderson, and L.M. Reder
"Priming, Perceptual Reversal, and Circular Reaction in a Neural Network Model of Schema-Based Vision"
W.K. Leow and R. Miikkulainen
"Variation in Unconscious Lexical Processing: Education and Experience Make a Difference"
G. Libben and L. Sveinson
"Cognitive Development and Infinity in the Small: Paradoxes and Consensus"
R. Nunez
"Probabilistic Reasoning Under Ignorance"
M. Ramoni, A. Riva, and V.L. Patel
"The Guessing Game: A Paradigm for Artificial Grammar Learning"
M. Redington and N. Chater
"Educational Implications of CELIA: Learning by Observing and Explaining"
M. Redmond
"Improving Design With Artifact History"
B.N. Reeves
"Explanatory AI, Indexical Reference, and Perception"
L.D. Roberts
"Learning Features of Representation in Conceptual Context"
L. Rodet and P.G. Schyns
"Tractable Learning of Probability Distributions Using the Contrastive Hebbian Algorithm"
C.E.L. Stark and J.L. McClelland
"Limiting Nested Beliefs in Cooperative Dialogue"
J.A. Taylor and J.C. Carletta
"Exploiting Problem Solving to Select Information to Include in Dialogues Between Cooperating Agents"
E.H. Turner
"STEPS: A Preliminary Model of Learning From a Tutor"
S. Ur and K. VanLehn
"Explaining Serendipitous Recognition in Design"
L.M. Wills and J.L. Kolodner
"Towards a Principled Representation of Discourse Plans"
R.M. Young, J.D. Moore, and M.E. Pollack
"The Representation of Relational Information"
J. Zhang and D.A. Norman
Tuesday, August 16, 1994
9:00am-10:30am
Plenary Speaker: Michael Pazzani
"The Role of Existing Knowledge in Generalization"
10:30am-11:00am
Break
11:00am-12:30pm
Symposium
"Collaborative Knowledge"
P. Thagard, Chair; K. Dunbar, E. Hutchins, G. Olson
11:00am-12:30pm
Paper Presentations
Topic: Learning
"Learning from Instruction: A Comprehension-Based Approach"
S.M. Doane, Y.W. Sohn, D. Adams, and D.S. McNamara
"Collaborative Explanations and Metacognition: Identifying Successful Learning Activities in the Acquisition of Cognitive Skills"
K. Bielaczyc, P.L. Pirolli, and A.L. Brown
"Towards a Computer Model of Memory Search Strategy Learning"
D.B. Leake
"Machines That Forget: Learning From Retrieval Failure of Mis-Indexed Explanations"
M.T. Cox
"Learning With Friends and Foes"
M. Sekaran and S. Sen
11:00am-12:30pm
Paper Presentations
Topic: Belief Modeling
"The Effect of Syntactic Form on Simple Belief Revisions and Updates"
R. Elio and F.J. Pelletier
"Combining Simulative and Metaphor-Based Reasoning About Beliefs"
J.A. Barnden, S. Helmreich, E. Iverson, and G.C. Stein
"Empirical Evidence Regarding the Folk Psychological Concept of Belief"
C. Hewson
"Belief Modelling, Intentionality and Perlocution in Metaphor Comprehension"
T. Veale and M.T. Keane
"SL: A Subjective, Intensional Logic of Belief"
H. Chalupsky and S.C. Shapiro
11:00am-12:30pm
Poster Presentations with Discussant
Topic: Syntactic Processing
"Context Effects in Syntactic Ambiguity Resolution: The Location of Prepositional Phrase Attachment"
E.C. Ferstl
"A Connectionist Model of Verb Subcategorization"
H. Schutze
"A Corpus Analysis of Recency Preference and Predicate Proximity"
E. Gibson and J. Loomis
"Inducing Agrammatic Profiles in Normals"
A. Blackwell and E. Bates
"Modeling the Use of Frequency and Contextual Biases in Sentence Processing"
N.J. Pearlmutter, K.G. Daugherty, M.C. MacDonald, and M.S. Seidenberg
"Immediate Effects of Discourse and Semantic Context in Syntactic Processing: Evidence from Eye-Tracking"
M. Spivey-Knowlton and M. Tanenhaus
"Parafoveal and Semantic Effects on Syntactic Ambiguity Resolution"
C. Burgess, M.K. Tanenhaus, and M. Hoffman
12:30pm-2:00pm
Lunch
2:00pm-3:30pm
Plenary Panel
"Cognitive Science 2004: The Last 10 Years"
T. Simon, Chair; J. Bates, D. Gentner, J. Greeno, G. Harman, M. Pazzani, W. Schneider
------------------------------
End of ML-LIST (Digest format)
****************************************
