Computational Learning Theory

This an introduction to the theory of computational learning.

Sommario

1. Concepts, hypotheses, learning algorithms; 2. Boolean formulae and representations; 3. Probabilistic learning; 4. Consistent algorithms and learnability; 5. Efficient learning I; 6. Efficient learning II; 7. The VC dimension; 8. Learning and the VC dimension; 9. VC dimension and efficient learning; 10. Linear threshold networks.

Riassunto

This is a self contained volume in which the authors concentrate on the 'probably approximately correct model'. It will therefore form an introduction to the theory of computational learning, suitable for a broad spectrum of graduate students from theoretical computer science and mathematics.

Dettagli sul prodotto

• Autori: M. H. G. Anthony, N. Biggs, Norman L. Biggs
• Con la collaborazione di: C. J. van Rijsbergen (Editore), C. J. van Rijsbergen (Editore)
• Editore: Cambridge University Press
• Lingue: Inglese
• Formato: Tascabile
• Pubblicazione: 10.01.2011
• EAN: 9780521599221
• ISBN: 978-0-521-59922-1
• Pagine: 172
• Dimensioni: 170 mm x 244 mm x 10 mm
• Peso: 309 g
• Serie: Cambridge Tracts in Theoretica
• Categorie: Guide e manuali; Scienze naturali, medicina, informatica, tecnica > Informatica, EDP > Informatica