OpenAIR @ RGU >
Design and Technology >
Journal articles (Engineering) >
Please use this identifier to cite or link to this item:
|Title: ||Incremental growth in modular neural networks.|
|Authors: ||MacLeod, Christopher|
Maxwell, Grant M.
|Keywords: ||Genetic algorithm|
Modular artificial neural network
|Issue Date: ||Jun-2009|
|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.|
|Appears in Collections:||Journal articles (Engineering)|
All items in OpenAIR are protected by copyright, with all rights reserved.