Special Issue on Algorithmic Learning Theory for ALT 2003

Special Issue on

for ALT 2003 in

Theoretical Computer Science

appeared as:

Theoretical Computer Science, Volume 364, Issue 1, November 2006.

The Special Issue on Algorithmic Learning Theory for ALT 2003 has been edited by Richard Gavaldà and Eiji Takimoto

Richard Gavaldà and Eiji Takimoto, Foreword	pp. 1-2

Ilia Nouretdinov and Vladimir Vovk, Criterion of calibration for transductive confidence machine with limited feedback	pp. 3-9

Vladimir Vovk, Well-calibrated predictions from on-line compression models	pp. 10-26

Marcus Hutter, On generalized computable universal priors and their convergence	pp. 27-41

Sandra Zilles, An approach to intrinsic complexity of uniform learning	pp. 42-61

Eric Martin, Arun Sharma, and Frank Stephan, On ordinal VC-dimension and some notions of complexity	pp. 62-76

Thomas Zeugmann, From learning in the limit to stochastic finite learning	pp. 77-97

Jin Uemura and Masako Sato, Learning of erasing primitive formal systems from positive examples	pp. 98-114

John Case, Sanjay Jain, Rüdiger Reischuk, Frank Stephan, and Thomas Zeugmann, Learning a subclass of regular patterns in polynomial time	pp. 115-131

Genshiro Kitagawa Signal extraction and knowledge discovery based on statistical modeling	pp. 132-142

back to the ALT Archives page