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.
Author(s): Thomas Eiter (auth.), Ricard Gavaldá, Klaus P. Jantke, Eiji Takimoto (eds.)
Series: Lecture Notes in Computer Science 2842 : Lecture Notes in Artificial Intelligence
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 2003
Language: English
Pages: 320
Tags: Artificial Intelligence (incl. Robotics); Computation by Abstract Devices; Algorithm Analysis and Problem Complexity; Mathematical Logic and Formal Languages; Document Preparation and Text Processing
Front Matter....Pages -
Abduction and the Dualization Problem....Pages 1-2
Signal Extraction and Knowledge Discovery Based on Statistical Modeling....Pages 3-14
Association Computation for Information Access....Pages 15-15
Efficient Data Representations That Preserve Information....Pages 16-16
Can Learning in the Limit Be Done Efficiently?....Pages 17-38
Intrinsic Complexity of Uniform Learning....Pages 39-53
On Ordinal VC-Dimension and Some Notions of Complexity....Pages 54-68
Learning of Erasing Primitive Formal Systems from Positive Examples....Pages 69-83
Changing the Inference Type – Keeping the Hypothesis Space....Pages 84-98
Robust Inference of Relevant Attributes....Pages 99-113
Efficient Learning of Ordered and Unordered Tree Patterns with Contractible Variables....Pages 114-128
On the Learnability of Erasing Pattern Languages in the Query Model....Pages 129-143
Learning of Finite Unions of Tree Patterns with Repeated Internal Structured Variables from Queries....Pages 144-158
Kernel Trick Embedded Gaussian Mixture Model....Pages 159-174
Efficiently Learning the Metric with Side-Information....Pages 175-189
Learning Continuous Latent Variable Models with Bregman Divergences....Pages 190-204
A Stochastic Gradient Descent Algorithm for Structural Risk Minimisation....Pages 205-220
On the Complexity of Training a Single Perceptron with Programmable Synaptic Delays....Pages 221-233
Learning a Subclass of Regular Patterns in Polynomial Time....Pages 234-246
Identification with Probability One of Stochastic Deterministic Linear Languages....Pages 247-258
Criterion of Calibration for Transductive Confidence Machine with Limited Feedback....Pages 259-267
Well-Calibrated Predictions from Online Compression Models....Pages 268-282
Transductive Confidence Machine Is Universal....Pages 283-297
On the Existence and Convergence of Computable Universal Priors....Pages 298-312
Back Matter....Pages -
