OpenAIR @ RGU >
Design and Technology >
Engineering >
Journal articles (Engineering) >

Please use this identifier to cite or link to this item:
This item has been viewed 118 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
MacLeod EEAI June2009.pdf264 kBAdobe PDFView/Open
Title: Incremental growth in modular neural networks.
Authors: MacLeod, Christopher
Maxwell, Grant M.
Muthuraman, Sethuraman
Keywords: Genetic algorithm
Modular artificial neural network
Incremental growth
Incremental evolution
Evolutionary algorithm
Issue Date: Jun-2009
Publisher: Elsevier
Citation: MACLEOD, C., MAXWELL, G. M., and MUTHURAMAN, S., 2009. Incremental growth in modular neural networks. Engineering Applications of Artificial Intelligence, 22 (4/5), pp. 660-666.
Abstract: This paper outlines an algorithm for incrementally growing Artificial Neural Networks. The algorithm allows the network to expand by adding new sub-networks or modules to an existing structure; the modules are trained using an Evolutionary Algorithm. Only the latest module added to the network is trained, the previous structure remains fixed. The algorithm allows information from different data domains to be integrated into the network and because the search space in each iteration is small, large and complex networks with a modular structure can emerge naturally. The paper describes an application of the algorithm to a legged robot and discusses its biological inspiration.
ISSN: 0952-1976
Appears in Collections:Journal articles (Engineering)

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