Proceedings of the Fourth International Workshop on MACHINE LEARNING

Proceedings of the Fourth International Workshop on Machine Learning provides careful theoretical analyses that make clear contact with traditional problems in machine learning. This book discusses the key role of learning in cognition.

Organized into 39 chapters, this book begins with an overview of pattern recognition systems of necessity that incorporate an approximate-matching process to determine the degree of similarity between an unknown input and all stored references. This text then describes the rationale in the Protos system for relegating inductive learning and deductive problem solving to minor roles in support of retaining, indexing and matching exemplars. Other chapters consider the power as well as the appropriateness of exemplar-based representations and their associated acquisition methods. This book discusses as well the extensions to the way a case is classified by a decision tree that address shortcomings. The final chapter deals with the advances in machine learning research.

This book is a valuable resource for psychologists, scientists, theorists, and research workers.

Preface: The Emerging Science of Machine Learning

Learning and Classification Exemplar-Based Approaches

Learning About Speech Sounds: The NEXUS Project

PROTOS: An Exemplar-Based Learning Apprentice

Learning Representative Exemplars of Concepts: An Initial Case Study

Probabilistic Approaches

Decision Trees as Probabilistic Classifiers

Conceptual Clustering, Learning from Examples, and Inference

How to Learn Imprecise Concepts: A Method for Employing a Two-Tiered Knowledge Representation in Learning

Quasi-Darwinian Learning in a Classifier System

Concept Learning and Bias

More Robust Concept Learning Using Dynamically-Variable Bias

Incremental Adjustment of Representations for Learning

Learning, Problem Solving, and Planning Heuristic Search Approaches

Concept Learning in Context

Strategy Learning with Multilayer Connectionist Representations

Learning a Preference Predicate

Planning Approaches

Acquiring Effective Search Control Rules: Explanation-Based Learning in the PRODIGY System

The Anatomy of a Weak Learning Method for Use in Goal Directed Search

Learning and Reusing Explanations

Problem Reduction Approaches

LT Revisited: Experimental Results of Applying Explanation-Based Learning to the Logic of Principia Mathematica

What is an Explanation in DISCIPLE?

Extending Problem Solver Capabilities Through Case-Based Inference

Learning and Natural Language

Learning to Integrate Syntax and Semantics

How Do Machine-Learning Paradigms Fare in Language Acquisition?

The Acquisition of Polysemy

Machine Discovery Observational Discovery

Cirrus: An Automated Protocol Analysis Tool

Scientific Theory Formation Through Analogical Inference

Inducing Causal and Social Theories: A Prerequisite for Explanation-based Learning

The Role of Abstractions in Learning Qualitative Models

Discovery and Experimentation

Learning by Experimentation

Observation and Generalisation in a Simulated Robot World

Empirical and Analytic Discovery in IL

Combining Many Searches in the FAHRENHEIT Discovery System

Cognitive Architectures for Learning

Causal Analysis and Inductive Learning

Varieties of Learning in Soar: 1987

Hill-Climbing Theories of Learning

Overviews

Bias, Version Spaces and Valiant's Learning Framework

Recent Results on Boolean Concept Learning

Machine Learning from Structured Objects

A New Approach to Unsupervised Learning in Deterministic Environments

Searching for Operational Concept Descriptions in BAR, MetaLEX, and EBG

Explanation-Based Generalization as Resolution Theorem Proving

Analogy and Single-Instance Generalization

Index