Advances in Artificial Intelligence: 11th Biennial Conference of the Canadian Society for Computational Studies of Intelligence, AI'96, Toronto, Canada, May (21-24), 1996. ProceedingsThis book constitutes the refereed proceedings of the 11th Biennial Conference of the Canadian Society for Computational Studies of Intelligence, AI 96, held in Toronto, Ontario, Canada, in May 1996. The 35 revised full papers presented in the book were carefully selected by the program committee. Although organized by a national society, AI 96 attracted contributions and participants with a significant geographic diversity. The issues addressed in this volume cover an electic range of current AI topics with a certain emphasis on various aspects of knowledge representation, natural language processing, and learning. |
Contents
ConstraintDirected Improvisation | 1 |
A New Model of Hard Binary Constraint | 14 |
Reasoning with MultiPoint Events | 26 |
介 | 29 |
Reasoning about Unknown Counterfactual and | 54 |
The Frame Problem and Bayesian Network | 69 |
Automatic Generation of a Complex | 84 |
A Chart Generator for Shake and Bake | 97 |
Efficient Algorithms for Qualitative Reasoning | 309 |
X | 318 |
A General Purpose Reasoner for Abstraction | 323 |
Reference Constraints and Individual Level | 336 |
Decision Tree Learning System with Switching | 349 |
3232 | 360 |
The Problem that Wont Go Away | 362 |
Fig 3 Posttraining meanerror curves | 368 |
2 | 109 |
CorpusBased Learning of Generalized Parse | 121 |
NP | 127 |
PARSETALK about Functional Anaphora | 133 |
KnowledgeBased Approaches to Query Expansion | 146 |
Acknowledgments | 158 |
Inferring What a User Is Not Interested in | 159 |
Developing an Expert System Technology for Industrial | 172 |
Planning and Learning in a Natural Resource | 187 |
A Hierarchical Model of Agent Based on Skill | 200 |
Semantics of Multiply Sectioned Bayesian | 213 |
A Statistical Method for | 227 |
and | 229 |
000 | 237 |
Efficient Induction of Recursive Prolog Definitions | 240 |
learning classification constructive induction | 249 |
Reinforcement Learning for RealWorld Control | 257 |
Walking robot | 268 |
A TwoLevel Approach to Learning in | 271 |
equipped with the environment tracking scheme | 282 |
Learning Classifications from Multiple Sources | 284 |
Paraconsistent Circumscription | 296 |
A PolynomialTime PredicateLogic | 375 |
G | 379 |
Enhancing Maximum Satisfiability Algorithms | 388 |
Searching with Pattern Databases | 402 |
A System for LogicBased Decision Modelling | 417 |
Attribute Selection Strategies for | 429 |
Automating Model Acquisition by Fault Knowledge Re | 442 |
Planning Algorithms and Planning Problems | 457 |
Lecture Notes in Mathematics | 460 |
ISBN 3540413855 | 464 |
Introduction | 467 |
Contents | xv |
1 Modeling of Electrorheological Fluids | 1 |
p 2 B | 30 |
In the picture below we have depicted the restrictions on | 36 |
2 Mathematical Framework | 39 |
3 Electrorheological Fluids with Shear | 61 |
4 Electrorheological Fluids with Shear | 105 |
5 Appendix | 153 |
| 165 | |
Common terms and phrases
abstract action agent algorithm anaphora applied approach Artificial Intelligence attribute axioms background knowledge Bayesian networks clauses Clausius-Duhem inequality complete component Computer concept consistent coreference CSPs database decision tree defined denote dialogue domain edge electrorheological fluids environment estimates example fluent function given global goal haze-order graph heuristic hierarchy implementation inequality inference input interestingness International Knowledge Representation knowledge-base labels Lemma logic programming lower bound Machine Learning mapping method minimal MSBN Negoplan nodes nonmonotonic obtain operator output paraconsistent logic parse performance phase transition possible predicate problem proof query query expansion reasoning reference constraints relation represent representation retrieval rule Růžička satisfied Section semantic sentence situation calculus Sobolev spaces solution space strategies structure subnets Theorem theory unsupervised learning variables