13. ALT 2002: Lübeck, Germany

@proceedings{DBLP:conf/alt/2002,
  editor    = {Nicol{\`o} Cesa-Bianchi and
               Masayuki Numao and
               R{\"u}diger Reischuk},
  title     = {Algorithmic Learning Theory, 13th International Conference, ALT
               2002, L{\"u}beck, Germany, November 24-26, 2002, Proceedings},
  booktitle = {ALT},
  publisher = {Springer},
  series    = {Lecture Notes in Computer Science},
  volume    = {2533},
  year      = {2002},
  isbn      = {3-540-00170-0},
  bibsource = {DBLP, http://dblp.uni-trier.de}
}

• Nicolò Cesa-Bianchi, Masayuki Numao, Rüdiger Reischuk:
  Editors' Introduction. 1-6
  

Invited Papers

• Susumu Hayashi:
  Mathematics Based on Learning. 7-21
  
• Rudolf Kruse, Christian Borgelt:
  Data Mining with Graphical Models. 22
  
• John Shawe-Taylor, Christopher K. I. Williams, Nello Cristianini, Jaz S. Kandola:
  On the Eigenspectrum of the Gram Matrix and Its Relationship to the Operator Eigenspectrum. 23-40
  
• Gerhard Widmer:
  In Search of the Horowitz Factor: Interim Report on a Musical Discovery Project. 41
  
• Ian H. Witten:
  Learning Structure from Sequences, with Applications in a Digital Library. 42-56
  

Regular Contributions

Learning Boolean Functions

• Kazuyuki Amano, Akira Maruoka:
  On Learning Monotone Boolean Functions under the Uniform Distribution. 57-68
  
• Rocco A. Servedio:
  On Learning Embedded Midbit Functions. 69-82
  
• Nader H. Bshouty, Lynn Burroughs:
  Maximizing Agreements and CoAgnostic Learning. 83-97
  

Boosting and Margin-Based Learning

• Dmitry Gavinsky:
  Optimally-Smooth Adaptive Boosting and Application to Agnostic Learning. 98-112
  
• Jyrki Kivinen, Alex J. Smola, Robert C. Williamson:
  Large Margin Classification for Moving Targets. 113-127
  
• Jürgen Forster, Hans-Ulrich Simon:
  On the Smallest Possible Dimension and the Largest Possible Margin of Linear Arrangements Representing Given Concept Classes Uniform Distribution. 128-138
  

Learning with Queries

• Johannes Köbler, Wolfgang Lindner:
  A General Dimension for Approximately Learning Boolean Functions. 139-148
  
• Johannes Köbler, Wolfgang Lindner:
  The Complexity of Learning Concept Classes with Polynomial General Dimension. 149-163
  
• Yuri Kalnishkan, Michael V. Vyugin:
  On the Absence of Predictive Complexity for Some Games. 164-172
  

Learning and Information Extraction

• Gunter Grieser, Klaus P. Jantke, Steffen Lange:
  Consistency Queries in Information Extraction. 173-187
  
• Yusuke Suzuki, Takayoshi Shoudai, Tomoyuki Uchida, Tetsuhiro Miyahara:
  Ordered Term Tree Languages which Are Polynomial Time Inductively Inferable from Positive Data. 188-202
  

Inductive Inference

• Gunter Grieser:
  Reflective Inductive Inference of Recursive Functions. 203-217
  
• Sanjay Jain, Wolfram Menzel, Frank Stephan:
  Classes with Easily Learnable Subclasses. 218-232
  
• Valentina S. Harizanov, Frank Stephan:
  On the Learnability of Vector Spaces. 233-247
  
• Eric Martin, Arun Sharma, Frank Stephan:
  Learning, Logic, and Topology in a Common Framework. 248-262
  

Inductive Logic Programming

• Johannes Fürnkranz:
  A Pathology of Bottom-Up Hill-Climbing in Inductive Rule Learning. 263-277
  
• Bertram Fronhöfer, Akihiro Yamamoto:
  Minimised Residue Hypotheses in Relevant Logic. 278-292
  

Language Learning

• Jin Uemura, Masako Sato:
  Compactness and Learning of Classes of Unions of Erasing Regular Pattern Languages. 293-307
  
• Daniel Reidenbach:
  A Negative Result on Inductive Inference of Extended Pattern Languages. 308-320
  

Statistical Learning

• Michael Schmitt:
  RBF Neural Networks and Descartes' Rule of Signs. 321-335
  
• Vladimir Vovk:
  Asymptotic Optimality of Transductive Confidence Machine. 336-350
  
• Sanjoy Dasgupta, Elan Pavlov, Yoram Singer:
  An Efficient PAC Algorithm for Reconstructing a Mixture of Lines. 351-364
  
• Sariel Har-Peled, Dan Roth, Dav Zimak:
  Constraint Classification: A New Approach to Multiclass Classification. 365-379
  
• Dietrich Braess, Jürgen Forster, Tomas Sauer, Hans-Ulrich Simon:
  How to Achieve Minimax Expected Kullback-Leibler Distance from an Unknown Finite Distribution. 380-394
  

Applications and Heuristics

• Tony Lindgren, Henrik Boström:
  Classification with Intersecting Rules. 395-402
  
• Rémi Coulom:
  Feedforward Neural Networks in Reinforcement Learning Applied to High-Dimensional Motor Control. 403-414