OpenAIR @ RGU >
Design and Technology >
Computing >
Conference publications (Computing) >

Please use this identifier to cite or link to this item:
This item has been viewed 10 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
Appendix A - 1st paper - An approach to evolvable neural functionality.pdf219.06 kBAdobe PDFView/Open
Title: An approach to evolvable neural functionality.
Authors: Capanni, Niccolo Francesco
MacLeod, Christopher
Maxwell, Grant M.
Keywords: Evolutionary networks
Neural functionality
Artificial neural networks
Issue Date: 2003
Publisher: Springer
Citation: CAPANNI, N., MACLEOD, C. and MAXWELL, G., 2003. An approach to evolvable neural functionality. In: O. KAYNAK, E. ALPAYDIN, E. OJA and L. XU, eds. Artificial neural networks and neural information processing – supplementary proceedings ICANN/ICONIP 2003. 26-29 June 2003. Istanbul, Turkey. pp. 220- 223.
Abstract: This paper outlines a neural model, which has been designed to be flexible enough to assume most mathematical functions. This is particularly useful in evolutionary networks as it allows the network complexity to increase without adding neurons. Theory and results are presented, showing the development of both time series and non-time dependent applications.
Appears in Collections:Conference publications (Computing)

All items in OpenAIR are protected by copyright, with all rights reserved.


   Disclaimer | Freedom of Information | Privacy Statement |Copyright ©2012 Robert Gordon University, Garthdee House, Garthdee Road, Aberdeen, AB10 7QB, Scotland, UK: a Scottish charity, registration No. SC013781