This book provides a systematic approach to knowledge representation, computation, and learning using higher-order logic. For those interested in computational logic, it provides a framework for knowledge representation and computation based on higher-order logic, and demonstrates its advantages over more standard approaches based on first-order logic. For those interested in machine learning, the book explains how higher-order logic provides suitable knowledge representation formalisms and hypothesis languages for machine learning applications.
Dieser Download kann aus rechtlichen Gründen nur mit Rechnungsadresse in A, B, BG, CY, CZ, D, DK, EW, E, FIN, F, GR, HR, H, IRL, I, LT, L, LR, M, NL, PL, P, R, S, SLO, SK ausgeliefert werden.
From the reviews of the third edition: "John has tried his hand at machine learning, and his aim in Logic for Learning is to demonstrate 'the rich and fruitful interplay between the fields of computational logic and machine learning'. ... As such, the book is more geared towards computational logicians who are interested in machine learning ... . The book can also be used as a textbook in a mathematically oriented advanced graduate course. ... it is indeed great stuff, which deserves to be taken serious by any computational logician ... ." (Peter Flach, TLP - Theory and Practice of Logic Programming, Issue 4, 2004) From the reviews: "This book provides a systematic approach to knowledge representation, computation, and learning using higher-order logic. It is aimed at researchers, graduate students, and senior undergraduates working in computational logic and/or machine learning." (PHINEWS, Vol. 3, April, 2003)