Special Issue on Algorithmic Learning Theory for ALT 2002

Special Issue on

for ALT 2002 in

Theoretical Computer Science

appeared as:

Theoretical Computer Science, Volume 350, Issue 1, January 2006.

The Special Issue on Algorithmic Learning Theory (ALT 2002) has been edited by Nicolò Cesa-Bianchi, Rüdiger Reischuk and Thomas Zeugmann.

Nicolò Cesa-Bianchi, Rüdiger Reischuk and Thomas Zeugmann. Foreword,	pp. 1-2

Kazuyuki Amano and Akira Maruoka, On learning monotone Boolean functions under the uniform distribution, Abstract.	pp. 3-12

Rocco A. Servedio, On learning embedded midbit functions, Abstract.	pp. 13-23

Nader H. Bshouty and Lynn Burroughs, Maximizing agreements and coagnostic learning, Abstract.	pp. 24-39

Jürgen Forster and Hans Ulrich Simon, On the smallest possible dimension and the largest possible margin of linear arrangements representing given concept classes , Abstract.	pp. 40-48

Johannes Köbler, and Wolfgang Lindner, The complexity of learning concept classes with polynomial general dimension, Abstract.	pp. 49-62

Yusuke Suzuki, Takayoshi Shoudai, Tomoyuki Uchida and Tetsuhiro Miyahara, Ordered term tree languages which are polynomial time inductively inferable from positive data, Abstract.	pp. 63-90

Daniel Reidenbach A non-learnable class of E-pattern languages, Abstract.	pp. 91-102

Éric Martin, Arun Sharma and Frank Stephan, Unifying logic, topology and learning in Parametric logic, Abstract.	pp. 103-124

Susumu Hayashi Mathematics based on incremental learning—Excluded middle and inductive inference Abstract.	pp. 125-139

Bertram Fronhöfer and Akihiro Yamamoto Hypothesis finding with proof theoretical appropriateness criteria, Abstract.	pp. 140-162

back to the ALT Archives page