Regular Papers -- An Axiomatic Approach to Feature Term Generalization -- Lazy Induction of Descriptions for Relational Case-Based Learning -- Estimating the Predictive Accuracy of a Classifier -- Improving the Robustness and Encoding Complexity of Behavioural Clones -- A Framework for Learning Rules from Multiple Instance Data -- Wrapping Web Information Providers by Transducer Induction -- Learning While Exploring: Bridging the Gaps in the Eligibility Traces -- A Reinforcement Learning Algorithm Applied to Simplified Two-Player Texas Hold’em Poker -- Speeding Up Relational Reinforcement Learning through the Use of an Incremental First Order Decision Tree Learner -- Analysis of the Performance of AdaBoost.M2 for the Simulated Digit-Recognition-Example -- Iterative Double Clustering for Unsupervised and Semi-supervised Learning -- On the Practice of Branching Program Boosting -- A Simple Approach to Ordinal Classification -- Fitness Distance Correlation of Neural Network Error Surfaces: A Scalable, Continuous Optimization Problem -- Extraction of Recurrent Patterns from Stratified Ordered Trees -- Understanding Probabilistic Classifiers -- Efficiently Determining the Starting Sample Size for Progressive Sampling -- Using Subclasses to Improve Classification Learning -- Learning What People (Don’t) Want -- Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions -- Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences -- Consensus Decision Trees: Using Consensus Hierarchical Clustering for Data Relabelling and Reduction -- Learning of Variability for Invariant Statistical Pattern Recognition -- The Evaluation of Predictive Learners: Some Theoretical and Empirical Results -- An Evolutionary Algorithm for Cost-Sensitive Decision Rule Learning -- A Mixture Approach to Novelty Detection Using Training Data with Outliers -- Applying the Bayesian Evidence Framework to ?-Support Vector Regression -- DQL: A New Updating Strategy for Reinforcement Learning Based on Q-Learning -- A Language-Based Similarity Measure -- Backpropagation in Decision Trees for Regression -- Comparing the Bayes and Typicalness Frameworks -- Symbolic Discriminant Analysis for Mining Gene Expression Patterns -- Social Agents Playing a Periodical Policy -- Learning When to Collaborate among Learning Agents -- Building Committees by Clustering Models Based on Pairwise Similarity Values -- Second Order Features for Maximising Text Classification Performance -- Importance Sampling Techniques in Neural Detector Training -- Induction of Qualitative Trees -- Text Categorization Using Transductive Boosting -- Using Multiple Clause Constructors in Inductive Logic Programming for Semantic Parsing -- Using Domain Knowledge on Population Dynamics Modeling for Equation Discovery -- Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL -- A Unified Framework for Evaluation Metrics in Classification Using Decision Trees -- Improving Term Extraction by System Combination Using Boosting -- Classification on Data with Biased Class Distribution -- Discovering Admissible Simultaneous Equation Models from Observed Data -- Discovering Strong Principles of Expressive Music Performance with the PLCG Rule Learning Strategy -- Proportional k-Interval Discretization for Naive-Bayes Classifiers -- Using Diversity in Preparing Ensembles of Classifiers Based on Different Feature Subsets to Minimize Generalization Error -- Geometric Properties of Naive Bayes in Nominal Domains -- Invited Papers -- Support Vectors for Reinforcement Learning -- Combining Discrete Algorithmic and Probabilistic Approaches in Data Mining -- Statistification or Mystification? The Need for Statistical Thought in Visual Data Mining -- The Musical Expression Project: A Challenge for Machine Learning and Knowledge Discovery -- Scalability, Search, and Sampling: From Smart Algorithms to Active Discovery.

This book constitutes the refereed proceedings of the 12th European Conference on Machine Learning, ECML 2001, held in Freiburg, Germany, in September 2001. The 50 revised full papers presented together with four invited contributions were carefully reviewed and selected from a total of 140 submissions. Among the topics covered are classifier systems, naive-Bayes classification, rule learning, decision tree-based classification, Web mining, equation discovery, inductive logic programming, text categorization, agent learning, backpropagation, reinforcement learning, sequence prediction, sequential decisions, classification learning, sampling, and semi-supervised learning.