Hendrik Blockeel - Böcker

This book introduces a novel paradigm for machine learning and data mining called predictive clustering, which covers a broad variety of learning tasks and offers a fresh perspective on existing techniques.The book presents an informal introduction to predictive clustering, describing learning tasks and settings, and then continues with a formal description of the paradigm, explaining algorithms for learning predictive clustering trees and predictive clustering rules, as well as presenting the applicability of these learning techniques to a broad range of tasks. Variants of decision tree learning algorithms are also introduced. Finally, the book offers several significant applications in ecology and bio-informatics.The book is written in a straightforward and easy-to-understand manner, aimed at varied readership, ranging from researchers with an interest in machine learning techniques to practitioners of data mining technology in the areas of ecology and bioinformatics.

This book constitutes the refereed conference proceedings of the 13th International Conference on Intelligent Data Analysis, which was held in October/November 2014 in Leuven, Belgium. The 33 revised full papers together with 3 invited papers were carefully reviewed and selected from 70 submissions handling all kinds of modeling and analysis methods, irrespective of discipline. The papers cover all aspects of intelligent data analysis, including papers on intelligent support for modeling and analyzing data from complex, dynamical systems.

This book constitutes the refereed proceedings of the 7th European Conference on Principles and Practice of Knowledge Discovery in Databases, PKDD 2003, held in Cavtat-Dubrovnik, Croatia in September 2003 in conjunction with ECML 2003.The 40 revised full papers presented together with 4 invited contributions were carefully reviewed and, together with another 40 ones for ECML 2003, selected from a total of 332 submissions. The papers address all current issues in data mining and knowledge discovery in databases including data mining tools, association rule mining, classification, clustering, pattern mining, multi-relational classifiers, boosting, kernel methods, learning Bayesian networks, inductive logic programming, user preferences mining, time series analysis, multi-view learning, support vector machine, pattern mining, relational learning, categorization, information extraction, decision making, prediction, and decision trees.

This book constitutes the refereed proceedings of the 14th European Conference on Machine Learning, ECML 2003, held in Cavtat-Dubrovnik, Croatia in September 2003 in conjunction with PKDD 2003.The 40 revised full papers presented together with 4 invited contributions were carefully reviewed and, together with another 40 ones for PKDD 2003, selected from a total of 332 submissions. The papers address all current issues in machine learning including support vector machine, inductive inference, feature selection algorithms, reinforcement learning, preference learning, probabilistic grammatical inference, decision tree learning, clustering, classification, agent learning, Markov networks, boosting, statistical parsing, Bayesian learning, supervised learning, and multi-instance learning.

ILP 2007, the 17th Conference on Inductive Logic Programming, was held in Corvallis, Oregon, USA, June 19-21, and was collocated with the 24th Inter- tional Conferenceon Machine Learning.The programconsisted of 15 full and 14 short presentations, a poster session, keynote talks by Paolo Frasconi (Learning withKernelsandLogicalRepresentations)andDavidJensen(BeyondPrediction: Directions for Probabilistic and Relational Learning), and several joint sessions with ICML. Thirty-eight submissions were received this year, out of which ?fteen were accepted for publication in the proceedings as full papers and eleven as short papers.Inclusionin the proceedings was decided bytaking into accountnotonly the relevance and quality of the work described, but also the quality and level of maturityofthetext.Severalmoresubmissionswereacceptedaswork-in-progress presentations. Thus the 2007 edition of ILP continued the tradition of adopting high selectivity for published papers, while at the same time o?ering a forum for work in progress. All accepted papers were made available in temporary online proceedings during the conference.Revised versions of the submitted papers, incorporating feedback from discussions at the conference, are included either in the proce- ings of the conference (this volume) or, for a small number of selected papers, in a special issue of theMachine Learning journal (abstracts of these are included in this volume). Papers reporting on work in progress remain available in the online proceedings, athttp://pages.cs.wisc.edu/~shavlik/ilp07wip/.

This three-volume set LNAI 8188, 8189 and 8190 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2013, held in Prague, Czech Republic, in September 2013. The 111 revised research papers presented together with 5 invited talks were carefully reviewed and selected from 447 submissions. The papers are organized in topical sections on reinforcement learning; Markov decision processes; active learning and optimization; learning from sequences; time series and spatio-temporal data; data streams; graphs and networks; social network analysis; natural language processing and information extraction; ranking and recommender systems; matrix and tensor analysis; structured output prediction, multi-label and multi-task learning; transfer learning; bayesian learning; graphical models; nearest-neighbor methods; ensembles; statistical learning; semi-supervised learning; unsupervised learning; subgroup discovery, outlier detection and anomaly detection; privacy and security; evaluation; applications; and medical applications.

This three-volume set LNAI 8188, 8189 and 8190 constitutes the refereed proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2013, held in Prague, Czech Republic, in September 2013. The 111 revised research papers presented together with 5 invited talks were carefully reviewed and selected from 447 submissions. The papers are organized in topical sections on reinforcement learning; Markov decision processes; active learning and optimization; learning from sequences; time series and spatio-temporal data; data streams; graphs and networks; social network analysis; natural language processing and information extraction; ranking and recommender systems; matrix and tensor analysis; structured output prediction, multi-label and multi-task learning; transfer learning; bayesian learning; graphical models; nearest-neighbor methods; ensembles; statistical learning; semi-supervised learning; unsupervised learning; subgroup discovery, outlier detection and anomaly detection; privacy and security; evaluation; applications; and medical applications.