Machine Learning Principles and Techniques
Published on 9. March 1989
Book
Hardback
256 pages
978-0-412-30570-2 (ISBN)
Description
This book collates the findings of recent research and presents them for both students and computer professionals. The authors aims to convey the excitement of working in this area at the frontier of computer science. They also show how the techniques described can lead to practical results. The book is a guide for those setting out to write or use a computer system which, in some sense, learns to improve its performance. College and university students should also find it a useful survey of an active research field, whose results are beginning to have practical applications. This book should be of interest to undergraduate students of computer science, linguistics, philosophy and psychology; and computer professionals in industry who are considering applications for inductive learning techniques.
More details
Series
Language
English
Place of publication
London
United Kingdom
Target group
College/higher education
Professional and scholarly
Illustrations
illustrations, bibliography, index
Dimensions
Height: 230 mm
Weight
480 gr
ISBN-13
978-0-412-30570-2 (9780412305702)
Copyright in bibliographic data is held by Nielsen Book Services Limited or its licensors: all rights reserved.
Schweitzer Classification
Content
Part 1: Background; The logic of induction - Richard Forsyth; Machine induction as a form of knowledge acquisition in knowledge engineering - Anna Hart; Inductive learning: the user's perspective - Tomasz Arciszewski and M. Mustafa; Part 2: Biologically inspired systems; The evolution of intelligence - Richard Forsyth; Artificial evolution and artificial intelligence - Ingo Rechenberg; Learning and distributed memory: getting close to neurons - Igor Aleksander; Part 3: Automated discovery; Automated discovery - Kenneth Haase; The acquisition of natural language by machine - Chris Naylor; A computational model of creativity - Masoud Yazdani; Part 4: Long-term perspectives; The road to knowledge-rich learning - Roy Rada; Databases that learn - Derek Partridge; Cognitive architecture and connectionism - Ajit Narayanan; Machine learning: the next ten years - Dimitris Chorafas.