An Overview of Some Classical Growing Neural Networks and New Developments
The mapping capability of artificial neural networks (ANN) is dependent on their structure,i.e.,the number of layers and the number of hidden units.There is no formal way of computing network topology as a function of the complexity of a problem.It is usually selected by trial-and-error and can be rather time consuming.Basically,we make use of two mechanisms that may modify the topology of the network:growth and pruning.This paper gives an overview of some classical Growing Neural Networks (GNN) and their new developments.This kind of GNN is also called the ANN with incremental learning.Firstly,some classical GNN with supervised learning are outlined which includes tiling algorithm,tower algorithm,upstart algorithm,cascade-correlation algorithm,restricted coulomb energy network and resource-allocation network.Secondly,a class of classical GNN with unsupervised learning is reviewed,such as selforganizing surfaces,evolve self-organizing maps,incremental grid growing and growing hierarchical self-organizing map.Thirdly,the new developments of GNN,including both supervised learning and unsupervised learning,are surveyed.The conclusion is given at the end of the paper.
growing neural networks constructive neural networks supervised learning and unsupervised learning self-organizing maps
Xinjian Qiang Guojian Cheng Zheng Wang
School of Computer Science Xian Shiyou University Xian,Shaanxi,P.R.China
国际会议
上海
英文
351-355
2010-06-22（万方平台首次上网日期，不代表论文的发表时间）