Sciweavers

ALT
2002
Springer
14 years 9 months ago
On the Eigenspectrum of the Gram Matrix and Its Relationship to the Operator Eigenspectrum
Abstract. In this paper we analyze the relationships between the eigenvalues of the m × m Gram matrix K for a kernel k(·, ·) corresponding to a sample x1, . . . , xm drawn from ...
John Shawe-Taylor, Christopher K. I. Williams, Nel...
ALT
2002
Springer
14 years 9 months ago
Data Mining with Graphical Models
Abstract. The explosion of data stored in commercial or administrational databases calls for intelligent techniques to discover the patterns hidden in them and thus to exploit all ...
Rudolf Kruse, Christian Borgelt
ALT
2002
Springer
14 years 9 months ago
The Complexity of Learning Concept Classes with Polynomial General Dimension
The general dimension is a combinatorial measure that characterizes the number of queries needed to learn a concept class. We use this notion to show that any p-evaluatable concep...
Johannes Köbler, Wolfgang Lindner
ALT
2002
Springer
14 years 9 months ago
Large Margin Classification for Moving Targets
Jyrki Kivinen, Alex J. Smola, Robert C. Williamson
ALT
2002
Springer
14 years 9 months ago
Classes with Easily Learnable Subclasses
In this paper we study the question of whether identifiable classes have subclasses which are identifiable under a more restrictive criterion. The chosen framework is inductive ...
Sanjay Jain, Wolfram Menzel, Frank Stephan
ALT
2002
Springer
14 years 9 months ago
On the Learnability of Vector Spaces
The central topic of the paper is the learnability of the recursively enumerable subspaces of V∞/V , where V∞ is the standard recursive vector space over the rationals with (c...
Valentina S. Harizanov, Frank Stephan
ALT
2002
Springer
14 years 9 months ago
Constraint Classification: A New Approach to Multiclass Classification
Sariel Har-Peled, Dan Roth, Dav Zimak
ALT
2002
Springer
14 years 9 months ago
Optimally-Smooth Adaptive Boosting and Application to Agnostic Learning
We describe a new boosting algorithm that is the first such algorithm to be both smooth and adaptive. These two features make possible performance improvements for many learning ...
Dmitry Gavinsky
ALT
2002
Springer
14 years 9 months ago
How to Achieve Minimax Expected Kullback-Leibler Distance from an Unknown Finite Distribution
Abstract. We consider a problem that is related to the “Universal Encoding Problem” from information theory. The basic goal is to find rules that map “partial information”...
Dietrich Braess, Jürgen Forster, Tomas Sauer,...
ALT
2002
Springer
14 years 9 months ago
A Pathology of Bottom-Up Hill-Climbing in Inductive Rule Learning
In this paper, we close the gap between the simple and straight-forward implementations of top-down hill-climbing that can be found in the literature, and the rather complex strate...
Johannes Fürnkranz