Search Ebook here:

Machine Learning Proceedings 1993


Author: Ole Bonderup

Publisher: Morgan Kaufmann

Publish Date: 1st July 1993

ISBN-13: 9781483298627

Pages: 540

Language: English



Machine Learning: Proceedings of the Tenth International Conference covers the papers presented at the Tenth International Conference on Machine Learning, held at Amherst, Massachusetts in June 27-29, 1993. The book focuses on the advancements of techniques, practices, approaches, and methodologies in machine learning.The selection first offers information on automatic algorithm/model class selection, using decision trees to improve case-based learning, GALOIS, and multitask learning. Discussions focus on multitask connectionist learning in more detail; multitask decision trees; an algorithm for the incremental determination of the concept lattice; and empirical evaluation of GALOIS as a learning system. The text then examines the use of qualitative models to guide inductive learning; automation of path analysis for building causal models from data; and construction of hidden variables in Bayesian networks via conceptual clustering.The book ponders on synthesis of abstraction hierarchies for constraint satisfaction by clustering approximately equivalent objects; efficient domain-independent experimentation; learning search control knowledge for deep space network scheduling; and learning procedures from interactive natural language instructions.The selection is a dependable reference for researchers wanting to explore the field of machine learning.

Table of Contents

Preface Organizing Committee and Program Committee Workshops Schedule The Evolution of Genetic Algorithms: Towards Massive Parallelism ÉLÉNA: A Bottom-Up Learning Method Addressing the Selective Superiority Problem: Automatic Algorithm/Model Class Selection Using Decision Trees to Improve Case-Based Learning GALOIS: An Order-Theoretic Approach to Conceptual Clustering Multitask Learning: A Knowledge-Based Source of Inductive Bias Using Qualitative Models to Guide Inductive Learning Automating Path Analysis for Building Causal Models from Data Constructing Hidden Variables in Bayesian Networks Via Conceptual Clustering Learning Symbolic Rules Using Artificial Neural Networks Small Disjuncts in Action: Learning to Diagnose Errors in the Local Loop of the Telephone Network Concept Sharing: A Means to Improve Multi-Concept Learning Discovering Dynamics Synthesis of Abstraction Hierarchies for Constraint Satisfaction by Clustering Approximately Equivalent Objects SKICAT: A Machine Learning System for Automated Cataloging of Large Scale Sky Surveys Learning From Entailment: An Application to Propositional Horn Sentences Efficient Domain-Independent Experimentation Learning Search Control Knowledge for Deep Space Network Scheduling Learning Procedures from Interactive Natural Language Instructions Generalization Under Implication by Recursive Anti-Unification Supervised Learning and Divide-and-Conquer: A Statistical Approach Hierarchical Learning in Stochastic Domains: Preliminary Results Constraining Learning with Search Control Scaling Up Reinforcement Learning for Robot Control Overcoming Incomplete Perception with Utile Distinction Memory Explanation Based Learning: A Comparison of Symbolic and Neural Network Approaches Combinatorial Optimization in Inductive Concept Learning Decision Theoretic Subsampling for Induction on Large Databases Learning DNF Via Probabilistic Evidence Combination Explaining and Generalizing Diagnostic Decisions Combining Instance-Based and Model-Based Learning Data Mining of Subjective Agricultural Data Lookahead Feature Construction for Learning Hard Concepts Adaptive NeuroControl: How Black Box and Simple can it be An SE-Tree Based Characterization of the Induction Problem Density-Adaptive Learning and Forgetting Efficiently Inducing Determinations: A Complete and Systematic Search Algorithm that Uses Optimal Pruning Compiling Bayesian Networks into Neural Networks A Reinforcement Learning Method for Maximizing Undiscounted Rewards ATM Scheduling with Queuing Delay Predictions Online Learning with Random Representations Learning from Queries and Examples with Tree-Structured Bias Multi-Agent Reinforcement Learning: Independent Vs. Cooperative Agents Better Learners Use Analogical Problem Solving Sparingly Author Index Subject Index