Computational Learning Theory

1. Front Matter

   PDF

2. Sample compression, learnability, and the Vapnik-Chervonenkis dimension

   • Manfred Warmuth

   Pages 1-2

3. Learning boxes in high dimension

   • Amos Beimel, Eyal Kushilevitz

   Pages 3-15

4. Learning monotone term decision lists

   • David Guijarro, Víctor Lavín, Vijay Raghavan

   Pages 16-26

5. Learning matrix functions over rings

   • Nader H. Bshouty, Christino Tamon, David K. Wilson

   Pages 27-37

6. Learning from incomplete boundary queries using split graphs and hypergraphs

   • Robert H. Sloan, György Turán

   Pages 38-50

7. Generalization of the PAC-model for learning with partial information

   • Joel Ratsaby, Vitaly Maiorov

   Pages 51-65

8. Monotonic and dual-monotonic probabilistic language learning of indexed families with high probability

   • Léa Meyer

   Pages 66-78

9. Closedness properties in team learning of recursive functions

   • Juris Smotrovs

   Pages 79-93

10. Structural measures for games and process control in the branch learning model

    • Matthias Ott, Frank Stephan

    Pages 94-108

11. Learning under persistent drift

    • Yoav Freund, Yishay Mansour

    Pages 109-118

12. Randomized hypotheses and minimum disagreement hypotheses for learning with noise

    • Nicolò Cesa-Bianchi, Paul Fischer, Eli Shamir, Hans Ulrich Simon

    Pages 119-133

13. Learning when to trust which experts

    • David Helmbold, Stephen Kwek, Leonard Pitt

    Pages 134-149

14. On learning branching programs and small depth circuits

    • Francesco Bergadano, Nader H. Bshouty, Christino Tamon, Stefano Varricchio

    Pages 150-161

15. Learning nearly monotone k-term DNF

    • Jorge Castro, David Guijarro, Víctor Lavín

    Pages 162-170

16. Optimal attribute-efficient learning of disjunction, parity, and threshold functions

    • Ryuhei Uehara, Kensei Tsuchida, Ingo Wegener

    Pages 171-184

17. learning pattern languages using queries

    • Satoshi Matsumoto, Ayumi Shinohara

    Pages 185-197

18. On fast and simple algorithms for finding Maximal subarrays and applications in learning theory

    • Andreas Birkendorf

    Pages 198-209

19. A minimax lower bound for empirical quantizer design

    • Peter Bartlett, Tamás Linder, Gábor Lugosi

    Pages 210-222

20. Vapnik-Chervonenkis dimension of recurrent neural networks

    • Pascal Koiran, Eduardo D. Sontag

    Pages 223-237

This book constitutes the refereed proceedings of the Third European Conference on Computational Learning Theory, EuroCOLT'97, held in Jerusalem, Israel, in March 1997.
The book presents 25 revised full papers carefully selected from a total of 36 high-quality submissions. The volume spans the whole spectrum of computational learning theory, with a certain emphasis on mathematical models of machine learning. Among the topics addressed are machine learning, neural nets, statistics, inductive inference, computational complexity, information theory, and theoretical physics.

• Algorithmische Komplexität
• Algorithmisches Lernen
• Induktive Inferenz
• Neuronale Netze
• Sprachenlernen
• algorithm
• algorithms
• classification
• complexity
• computational complexity
• inductive inference
• information theory
• learning theory
• machine learning
• neural networks

Policies and ethics