Algorithmic Learning Theory

This volume contains the papers presented at the 14th Annual Conference on Algorithmic Learning Theory (ALT 2003), which was held in Sapporo (Japan) duringOctober17 19,2003. Themainobjectiveoftheconferencewastoprovide an interdisciplinary forum for discussing the theoretical foundations of machine learning as well as their relevance to practical applications. The conference was co-locatedwiththe6thInternationalConferenceonDiscoveryScience(DS2003). The volume includes 19 technical contributions that were selected by the program committee from 37 submissions. It also contains the ALT 2003 invited talks presented by Naftali Tishby (Hebrew University, Israel) on E?cient Data Representations that Preserve Information, by Thomas Zeugmann (University of Lub eck, Germany) on Can Learning in the Limit be Done E?ciently? , and by Genshiro Kitagawa (Institute of Statistical Mathematics, Japan) on S- nal Extraction and Knowledge Discovery Based on Statistical Modeling (joint invited talk with DS 2003). Furthermore, this volume includes abstracts of the invitedtalksforDS2003presentedbyThomasEiter(ViennaUniversityofTe- nology, Austria) on Abduction and the Dualization Problem and by Akihiko Takano (National Institute of Informatics, Japan) on Association Computation for Information Access. The complete versions of these papers were published in the DS 2003 proceedings (Lecture Notes in Arti?cial Intelligence Vol. 2843). ALT has been awarding theE. MarkGoldAward for the most outstanding paper by a student author since 1999. This year the award was given to Sandra Zilles for her paper Intrinsic Complexity of Uniform Learning. This conference was the 14th in a series of annual conferences established in 1990. ContinuationoftheALTseriesissupervisedbyitssteeringcommittee,c- sisting of: Thomas Zeugmann (Univ.

Klappentext

This book constitutes the refereed proceedings of the 14th International Conference on Algorithmic Learning Theory, ALT 2003, held in Sapporo, Japan in October 2003.The 19 revised full papers presented together with 2 invited papers and abstracts of 3 invited talks were carefully reviewed and selected from 37 submissions. The papers are organized in topical sections on inductive inference, learning and information extraction, learning with queries, learning with non-linear optimization, learning from random examples, and online prediction.

Inhalt
Invited Papers.- Abduction and the Dualization Problem.- Signal Extraction and Knowledge Discovery Based on Statistical Modeling.- Association Computation for Information Access.- Efficient Data Representations That Preserve Information.- Can Learning in the Limit Be Done Efficiently?.- Inductive Inference.- Intrinsic Complexity of Uniform Learning.- On Ordinal VC-Dimension and Some Notions of Complexity.- Learning of Erasing Primitive Formal Systems from Positive Examples.- Changing the Inference Type Keeping the Hypothesis Space.- Learning and Information Extraction.- Robust Inference of Relevant Attributes.- Efficient Learning of Ordered and Unordered Tree Patterns with Contractible Variables.- Learning with Queries.- On the Learnability of Erasing Pattern Languages in the Query Model.- Learning of Finite Unions of Tree Patterns with Repeated Internal Structured Variables from Queries.- Learning with Non-linear Optimization.- Kernel Trick Embedded Gaussian Mixture Model.- Efficiently Learning the Metric with Side-Information.- Learning Continuous Latent Variable Models with Bregman Divergences.- A Stochastic Gradient Descent Algorithm for Structural Risk Minimisation.- Learning from Random Examples.- On the Complexity of Training a Single Perceptron with Programmable Synaptic Delays.- Learning a Subclass of Regular Patterns in Polynomial Time.- Identification with Probability One of Stochastic Deterministic Linear Languages.- Online Prediction.- Criterion of Calibration for Transductive Confidence Machine with Limited Feedback.- Well-Calibrated Predictions from Online Compression Models.- Transductive Confidence Machine Is Universal.- On the Existence and Convergence of Computable Universal Priors.