Learning from Data

by Fisher, Doug; Lenz, Hans-J

• ISBN13: 9780387947365
• ISBN10: 0387947361
• Format: Paperback
• Copyright: 1996-06-01
• Publisher: Springer Verlag

Summary

This volume contains a revised collection of papers originally presented at the Fifth International Workshop on Artificial Intelligence and Statistics in 1995. The topics represented in this collection of 42 papers are diverse and include natural language applications, causality and graphical models, classification, learning, knowledge discovery, and exploratory data analysis. The papers illustrate the rich possibilities for interdisciplinary study at the interface of artificial intelligence and statistics.

Table of Contents

Preface
Two Algorithms for Inducing Structural Equation Models from Data	p. 3
Using Causal Knowledge to Learn More Useful Decision Rules from Data	p. 13
A Causal Calculus for Statistical Research	p. 23
Likelihood-based Causal Inference	p. 35
Ploxoma: Testbed for Uncertain Inference	p. 47
Solving Influence Diagrams Using Gibbs Sampling	p. 59
Modelling and Monitoring Dynamic Systems by Chain Graphs	p. 69
Propagation of Gaussian Belief Functions	p. 79
On Test Selection Strategies for Belief Networks	p. 89
Representing and Solving Asymmetric Decision Problems Using Valuation Networks	p. 99
A Hill-Climbing Approach for Optimizing Classification Trees	p. 109
Learning Bayesian Networks is NP-Complete	p. 121
Heuristic Search for Model Structure: The Benefits of Restraining Greed	p. 131
Learning Possibilistic Networks from Data	p. 143
Detecting Imperfect Patterns in Event Streams Using Local Search	p. 155
Structure Learning of Bayesian Networks by Hybrid Genetic Algorithms	p. 165
An Axiomatization of Loglinear Models with an Application to the Model-Search Problem	p. 175
Detecting Complex Dependencies in Categorical Data	p. 185
A Comparative Evaluation of Sequential Feature Selection Algorithms	p. 199
Classification Using Bayes Averaging of Multiple, Relational Rule-Based Models	p. 207
Picking the Best Expert from a Sequence	p. 219
Hierarchical Clustering of Composite Objects with a Variable Number of Components	p. 229
Searching for Dependencies in Bayesian Classifiers	p. 239
Statistical Analysis for Complex Systems in Biomedicine	p. 251
Learning in Hybrid Noise Environments Using Statistical Queries	p. 259
On the Statistical Comparison of Inductive Learning Methods	p. 271
Dynamical Selection of Learning Algorithms	p. 281
Learning Bayesian Networks Using Feature Selection	p. 291
Data Representations in Learning	p. 301
Rule Induction as Exploratory Data Analysis	p. 313
Non-Linear Dimensionality Reduction: A Comparative Performance Analysis	p. 323
Omega-Stat: An Environment for Implementing Intelligent Modelling Strategies	p. 333
Framework for a Generic Knowledge Discovery Toolkit	p. 343
Control Representation in an EDA Assistant	p. 353
A Further Comparison of Simplification Methods for Decision-Tree Induction	p. 365
Robust Linear Discriminant Trees	p. 375
Tree Structured Interpretable Regression	p. 387
An Exact Probability Metric for Decision Tree Splitting	p. 399
Two Applications of Statistical Modelling to Natural Language Processing	p. 413
A Model for Part-of-Speech Prediction	p. 423
Viewpoint-Based Measurement of Semantic Similarity Between Words	p. 433
Part-of-Speech Tagging from "Small" Data Sets	p. 443
Table of Contents provided by Blackwell. All Rights Reserved.