Ebook: Algorithmic Learning Theory: 15th International Conference, ALT 2004, Padova, Italy, October 2-5, 2004. Proceedings

Algorithmic learning theory is mathematics about computer programs which learn from experience. This involves considerable interaction between various mathematical disciplines including theory of computation, statistics, and c- binatorics. There is also considerable interaction with the practical, empirical ?elds of machine and statistical learning in which a principal aim is to predict, from past data about phenomena, useful features of future data from the same phenomena. The papers in this volume cover a broad range of topics of current research in the ?eld of algorithmic learning theory. We have divided the 29 technical, contributed papers in this volume into eight categories (corresponding to eight sessions) re?ecting this broad range. The categories featured are Inductive Inf- ence, Approximate Optimization Algorithms, Online Sequence Prediction, S- tistical Analysis of Unlabeled Data, PAC Learning & Boosting, Statistical - pervisedLearning,LogicBasedLearning,andQuery&ReinforcementLearning. Below we give a brief overview of the ?eld, placing each of these topics in the general context of the ?eld. Formal models of automated learning re?ect various facets of the wide range of activities that can be viewed as learning. A ?rst dichotomy is between viewing learning as an inde?nite process and viewing it as a ?nite activity with a de?ned termination. Inductive Inference models focus on inde?nite learning processes, requiring only eventual success of the learner to converge to a satisfactory conclusion.

---

This book constitutes the refereed proceedings of the 15th International Conference on Algorithmic Learning Theory, ALT 2004, held in Padova, Italy in October 2004.

The 29 revised full papers presented together with 5 invited papers and 3 tutorial summaries were carefully reviewed and selected from 91 submissions. The papers are organized in topical sections on inductive inference, PAC learning and boosting, statistical supervised learning, online sequence learning, approximate optimization algorithms, logic based learning, and query and reinforcement learning.

---

This book constitutes the refereed proceedings of the 15th International Conference on Algorithmic Learning Theory, ALT 2004, held in Padova, Italy in October 2004.

The 29 revised full papers presented together with 5 invited papers and 3 tutorial summaries were carefully reviewed and selected from 91 submissions. The papers are organized in topical sections on inductive inference, PAC learning and boosting, statistical supervised learning, online sequence learning, approximate optimization algorithms, logic based learning, and query and reinforcement learning.

Content:
Front Matter....Pages -
String Pattern Discovery....Pages 1-13
Applications of Regularized Least Squares to Classification Problems....Pages 14-18
Probabilistic Inductive Logic Programming....Pages 19-36
Hidden Markov Modelling Techniques for Haplotype Analysis....Pages 37-52
Learning, Logic, and Probability: A Unified View....Pages 53-53
Learning Languages from Positive Data and Negative Counterexamples....Pages 54-68
Inductive Inference of Term Rewriting Systems from Positive Data....Pages 69-82
On the Data Consumption Benefits of Accepting Increased Uncertainty....Pages 83-98
Comparison of Query Learning and Gold-Style Learning in Dependence of the Hypothesis Space....Pages 99-113
Learning r-of-k Functions by Boosting....Pages 114-126
Boosting Based on Divide and Merge....Pages 127-141
Decision Trees: More Theoretical Justification for Practical Algorithms....Pages 142-155
Application of Classical Nonparametric Predictors to Learning Conditionally I.I.D. Data....Pages 156-170
Complexity of Pattern Classes and Lipschitz Property....Pages 171-180
On Kernels, Margins, and Low-Dimensional Mappings....Pages 181-193
Estimation of the Data Region Using Extreme-Value Distributions....Pages 194-205
Maximum Entropy Principle in Non-ordered Setting....Pages 206-220
Universal Convergence of Semimeasures on Individual Random Sequences....Pages 221-233
A Criterion for the Existence of Predictive Complexity for Binary Games....Pages 234-248
Full Information Game with Gains and Losses....Pages 249-263
Prediction with Expert Advice by Following the Perturbed Leader for General Weights....Pages 264-278
On the Convergence Speed of MDL Predictions for Bernoulli Sequences....Pages 279-293
Relative Loss Bounds and Polynomial-Time Predictions for the k-lms-net Algorithm....Pages 294-308
On the Complexity of Working Set Selection....Pages 309-323
Convergence of a Generalized Gradient Selection Approach for the Decomposition Method....Pages 324-337
Newton Diagram and Stochastic Complexity in Mixture of Binomial Distributions....Pages 338-349
Learnability of Relatively Quantified Generalized Formulas....Pages 350-364
Learning Languages Generated by Elementary Formal Systems and Its Application to SH Languages....Pages 365-379
New Revision Algorithms....Pages 380-394
The Subsumption Lattice and Query Learning....Pages 395-409
Learning of Ordered Tree Languages with Height-Bounded Variables Using Queries....Pages 410-424
Learning Tree Languages from Positive Examples and Membership Queries....Pages 425-439
Learning Content Sequencing in an Educational Environment According to Student Needs....Pages 440-453
Statistical Learning in Digital Wireless Communications....Pages 454-463
A BP-Based Algorithm for Performing Bayesian Inference in Large Perceptron-Type Networks....Pages 464-478
Approximate Inference in Probabilistic Models....Pages 479-493
Back Matter....Pages 494-504
....Pages -