Machine Learning Proceedings 1990

"Chapter 1 Empirical Learning

Knowledge Acquisition from Examples Using Maximal Representation Learning

KBG: A Knowledge Based Generalizer

Performance Analysis of A Probabilistic Inductive Learning System

A Comparative Study of ID3 and Backpropagation for English Text-to-Speech Mapping

Learning from Data with Bounded Inconsistency

Conceptual Set Covering: Improving Fit-And-Split Algorithms

Incremental Learning of Rules and Meta-Rules

An Incremental Method for Finding Multivariate Splits for Decision Trees

Incremental Induction of Topologically Minimal Trees

Chapter 2 Conceptual Clustering

A Rational Analysis of Categorization

Search Control, Utility, and Concept Induction

Graph Clustering and Model Learning by Data Compression

Chapter 3 Constructive Induction and Reformulation

An Analysis of Representation Shift In Concept Learning

Learning Procedures by Environment-Driven Constructive Induction

Beyond Inversion of Resolution

Chapter 4 Genetic Algorithms

Genetic Programming

Improving the Performance of Genetic Algorithms in Automated Discovery of Parameters

Using Genetic Algorithms to Learn Disjunctive Rules from Examples

NEWBOOLE: A Fast GBML System

Chapter 5 Neural Network & Reinforcement Learning

Learning Functions in k-DNF from Reinforcement

Is Learning Rate a Good Performance Criterion for Learning?

Active Perception and Reinforcement Learning

Chapter 6 Learning and Planning

Learning Plans for Competitive Domains

Explanations of Empirically Derived Reactive Plans

Learning and Enforcement: Stabilizing Environments to Facilitate Activity

Simulation-Assisted Learning by Competition: Effects of Noise Differences Between Training Model and Target Environment

Integrated Architecture for Learning, Planning, and Reacting Based on Approximating Dynamic Programming

Chapter 7 Robot Learning

Reducing Real-World Failures of Approximate Explanation-Based Rules

Correcting and Extending Domain Knowledge Using Outside Guidance

Acquisition of Dynamic Control Knowledge for a Robotic Manipulator

Feature Extraction and Clustering of Tactile Impressions with Connectionist Models

Chapter 8 Explanation-Based Learning

Generalizing the Order of Goals as an Approach to Generalizing Number

Learning Approximate Control Rules of High Utility

Applying Abstraction and Simplification to Learn in Intractable Domains

Explanation-Based Learning with Incomplete Theories: A Three-Step Approach

Using Abductive Recovery of Failed Proof s for Problem Solving by Analogy

Issues in the Design of Operator Composition Systems

Incremental Learning of Explanation Patterns and Their Indices

Chapter 9 Explanation-Based and Empirical Learning

Integrated Learning in a Real Domain

Incremental Version-Space Merging

Average Case Analysis of Conjunctive Learning Algorithms

ILS: A Framework for Multi-Paradigmatic Learning

An Integrated Framework of Inducing Rules from Examples

Chapter 10 Language Learning

Adaptive Parsing: A General Method for Learning Idiosyncratic Grammars

A Comparison of Learning Techniques in Second Language Learning

Learning String Patterns and Tree Patterns from Examples

Learning with Discrete Multi-Valued Neurons

Chapter 11 Other Topics

The General Utility Problem in Machine Learning

A Robust Approach to Numeric Discovery

More Results on the Complexity of Knowledge Base Refinement: Belief Networks

Index