Machine Learning: ECML 2006: 17th European Conference on Machine Learning, Berlin, Germany, September 18-22, 2006, Proceedings

by Johannes Fürnkranz (Editor), Tobias Scheffer (Editor), Myra Spiliopoulou (Editor)

Overview

This book constitutes the refereed proceedings of the 17th European Conference on Machine Learning, ECML 2006, held, jointly with PKDD 2006. The book presents 46 revised full papers and 36 revised short papers together with abstracts of 5 invited talks, carefully reviewed and selected from 564 papers submitted. The papers present a wealth of new results in the area and address all current issues in machine learning.

Product Details

ISBN-13:	9783540453758
Publisher:	Springer Berlin Heidelberg
Publication date:	10/19/2006
Series:	Lecture Notes in Computer Science , #4212
Edition description:	2006
Pages:	851
Product dimensions:	6.10(w) x 9.25(h) x 0.36(d)

Table of Contents

Invited Talks.- On Temporal Evolution in Data Streams.- The Future of CiteSeer: CiteSeerx.- Learning to Have Fun.- Winning the DARPA Grand Challenge.- Challenges of Urban Sensing.- Long Papers.- Learning in One-Shot Strategic Form Games.- A Selective Sampling Strategy for Label Ranking.- Combinatorial Markov Random Fields.- Learning Shastic Tree Edit Distance.- Pertinent Background Knowledge for Learning Protein Grammars.- Improving Bayesian Network Structure Search with Random Variable Aggregation Hierarchies.- Sequence Discrimination Using Phase-Type Distributions.- Languages as Hyperplanes: Grammatical Inference with String Kernels.- Toward Robust Real-World Inference: A New Perspective on Explanation-Based Learning.- Fisher Kernels for Relational Data.- Evaluating Misclassifications in Imbalanced Data.- Improving Control-Knowledge Acquisition for Planning by Active Learning.- PAC-Learning of Markov Models with Hidden State.- A Discriminative Approach for the Retrieval of Imagesfrom Text Queries.- TildeCRF: Conditional Random Fields for Logical Sequences.- Unsupervised Multiple-Instance Learning for Functional Profiling of Genomic Data.- Bayesian Learning of Markov Network Structure.- Approximate Policy Iteration for Closed-Loop Learning of Visual Tasks.- Task-Driven Discretization of the Joint Space of Visual Percepts and Continuous Actions.- EM Algorithm for Symmetric Causal Independence Models.- Deconvolutive Clustering of Markov States.- Patching Approximate Solutions in Reinforcement Learning.- Fast Variational Inference for Gaussian Process Models Through KL-Correction.- Bandit Based Monte-Carlo Planning.- Bayesian Learning with Mixtures of Trees.- Transductive Gaussian Process Regression with Automatic Model Selection.- Efficient Convolution Kernels for Dependency and Constituent Syntactic Trees.- Why Is Rule Learning Optimistic and How to Correct It.- Automatically Evolving Rule Induction Algorithms.- Bayesian Active Learning for Sensitivity Analysis.- Mixtures of Kikuchi Approximations.- Boosting in PN Spaces.- Prioritizing Point-Based POMDP Solvers.- Graph Based Semi-supervised Learning with Sharper Edges.- Margin-Based Active Learning for Structured Output Spaces.- Skill Acquisition Via Transfer Learning and Advice Taking.- Constant Rate Approximate Maximum Margin Algorithms.- Batch Classification with Applications in Computer Aided Diagnosis.- Improving the Ranking Performance of Decision Trees.- Multiple-Instance Learning Via Random Walk.- Localized Alternative Cluster Ensembles for Collaborative Structuring.- Distributional Features for Text Categorization.- Subspace Metric Ensembles for Semi-supervised Clustering of High Dimensional Data.- An Adaptive Kernel Method for Semi-supervised Clustering.- To Select or To Weigh: A Comparative Study of Model Selection and Model Weighing for SPODE Ensembles.- Ensembles of Nearest Neighbor Forecasts.- Short Papers.- Learning Process Models with Missing Data.- Case-Based Label Ranking.-Cascade Evaluation of Clustering Algorithms.- Making Good Probability Estimates for Regression.- Fast Spectral Clustering of Data Using Sequential Matrix Compression.- An Information-Theoretic Framework for High-Order Co-clustering of Heterogeneous Objects.- Efficient Inference in Large Conditional Random Fields.- A Kernel-Based Approach to Estimating Phase Shifts Between Irregularly Sampled Time Series: An Application to Gravitational Lenses.- Cost-Sensitive Decision Tree Learning for Forensic Classification.- The Minimum Volume Covering Ellipsoid Estimation in Kernel-Defined Feature Spaces.- Right of Inference: Nearest Rectangle Learning Revisited.- Reinforcement Learning for MDPs with Constraints.- Efficient Non-linear Control Through Neuroevolution.- Efficient Prediction-Based Validation for Document Clustering.- On Testing the Missing at Random Assumption.- B-Matching for Spectral Clustering.- Multi-class Ensemble-Based Active Learning.- Active Learning with Irrelevant Examples.-Classification with Support Hyperplanes.- (Agnostic) PAC Learning Concepts in Higher-Order Logic.- Evaluating Feature Selection for SVMs in High Dimensions.- Revisiting Fisher Kernels for Document Similarities.- Scaling Model-Based Average-Reward Reinforcement Learning for Product Delivery.- Robust Probabilistic Calibration.- Missing Data in Kernel PCA.- Exploiting Extremely Rare Features in Text Categorization.- Efficient Large Scale Linear Programming Support Vector Machines.- An Efficient Approximation to Lookahead in Relational Learners.- Improvement of Systems Management Policies Using Hybrid Reinforcement Learning.- Diversified SVM Ensembles for Large Data Sets.- Dynamic Integration with Random Forests.- Bagging Using Statistical Queries.- Guiding the Search in the NO Region of the Phase Transition Problem with a Partial Subsumption Test.- Spline Embedding for Nonlinear Dimensionality Reduction.- Cost-Sensitive Learning of SVM for Ranking.- Variational Bayesian Dirichlet-Multinomial Allocation for Exponential Family Mixtures.

Editorial Reviews

From the reviews:

"In this book, we find many ways of representing machine learning from different fields, including active learning, algorithmic learning, case-based learning, classifier systems, clustering algorithms, decision-tree learning, inductive inference, kernel methods, knowledge discovery, multiple-instance learning, reinforcement learning, statistical learning, and support vector machines. Most of the current issues in machine learning research are discussed. … I strongly recommend this book for all researchers interested in the very best of machine learning studies." (Agliberto Cierco, ACM Computing Reviews, Vol. 49 (5), 2008)

From the Publisher