Integrating the key approaches of neural networks

Howard, Beverley Robin

dc.contributor.advisor	Wolvaardt, D. E. (Dirkie Elizabeth), 1945-
dc.contributor.author	Howard, Beverley Robin
dc.date.accessioned	2015-01-23T04:24:48Z
dc.date.available	2015-01-23T04:24:48Z
dc.date.issued	1999-12
dc.identifier.citation	Howard, Beverley Robin (1999) Integrating the key approaches of neural networks, University of South Africa, Pretoria, <http://hdl.handle.net/10500/16971>	en
dc.identifier.uri	http://hdl.handle.net/10500/16971
dc.description.abstract	The thesis is written in chapter form. Chapter 1 describes some of the history of neural networks and its place in the field of artificial intelligence. It indicates the biological basis from which neural network approximation are made. Chapter 2 describes the properties of neural networks and their uses. It introduces the concepts of training and learning. Chapters 3, 4, 5 and 6 show the perceptron and adaline in feedforward and recurrent networks particular reference is made to regression substitution by "group method data handling. Networks are chosen that explain the application of neural networks in classification, association, optimization and self organization. Chapter 7 addresses the subject of practical inputs to neural networks. Chapter 8 reviews some interesting recent developments. Chapter 9 reviews some ideas on the future technology for neural networks. Chapter 10 gives a listing of some neural network types and their uses. Appendix A gives some of the ideas used in portfolio selection for the Johannesburg Stock Exchange.	en
dc.format.extent	1 online resource (189 leaves)
dc.language.iso	en	en
dc.subject.ddc	006.32
dc.subject.lcsh	Neural networks (Computer science)	en
dc.subject.lcsh	Artificial intelligence	en
dc.title	Integrating the key approaches of neural networks	en
dc.type	Dissertation
dc.description.department	Computing
dc.description.degree	M. Sc. (Operations Research)