Growing RBF structures using self-organizing maps
Growing RBF structures using self-organizing maps
复制标题
使用自组织映射增长 RBF 结构
DOI：
10.1109/roman.2000.892479
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
J. Murata
中科院分区：
文献类型：
--
作者：
Qingyu Xiong;K. Hirasawa;Jinglu Hu;J. Murata
本文提出了一种新的基于自组织映射神经网络的RBF网络结构。它分别由SOM网络和RBF网络组成。SOM进行无监督学习，并将其输出节点的权向量传递给RBF网络的隐层节点作为RBF激活函数的中心，从而实现SOM输出节点与RBF网络隐层节点之间的一一对应关系。RBF网络使用delta规则进行监督训练。因此，RBF网络中的当前输出误差可以用于根据规则确定在何处插入新的SOM单元。这也使得有可能使RBF网络增长，直到满足性能标准或直到获得所需的网络大小。在双螺旋基准上的仿真结果证明了所提出的网络具有良好的性能。
We present a novel growing RBF network structure using SOM in this paper. It consists of SOM and RBF networks respectively. The SOM performs unsupervised learning and also the weight vectors belonging to its output nodes are transmitted to the hidden nodes in the RBF networks as the centers of RBF activation functions, as a result one to one correspondence relationship is realised between the output nodes in SOM and the hidden nodes in RBF networks. The RBF networks perform supervised training using delta rule. Therefore, the current output errors in the RBF networks can be used to determine where to insert a new SOM unit according to the rule. This also makes it possible to make the RBF networks grow until a performance criterion is fulfilled or until a desired network size is obtained. The simulations on the two-spirals benchmark are shown to prove the proposed networks have good performance.