Multilayer feedforward potential function network
Multilayer feedforward potential function network
复制标题
多层前馈势函数网络
DOI：
10.1109/icnn.1988.23844
复制
发表时间：
1988
期刊：
影响因子：
--
通讯作者：
R. Kil
中科院分区：
文献类型：
--
作者：
Sukhan Lee;R. Kil
作者提出了一种多层前馈网络，称为高斯势函数网络（GPFN），执行关联或分类的基础上合成的输入空间域的高斯势函数单元（GPFU）的数量的一组潜在的字段。GPFU作为GPFN的基本部件，被设计成产生高斯形式的势场。由适当数量的GPFU生成的高斯势场的加权求和在输入空间的域上提供任意形状的势场。作者还提出了一个详细的学习算法的GPFN。学习包括确定GPFU的最小必要数量以及调整由GPFU定义的各个高斯势场的位置和形状以及求和权重。最小所需GPFU数量的学习是基于对GPFU有效半径的控制，而参数学习是基于梯度下降过程。<<ETX>>
The authors present a multilayer feedforward network, called the Gaussian potential function network (GPFN), performing association or classification based on a set of potentially fields synthesized over the domain of input space by a number of Gaussian potential function units (GPFUs). A GPFU as a basic component of the GPFN is designed to generate a Gaussian form of a potential field. A weighted summation of Gaussian potential fields generated by a suitable number of GPFUs provides an arbitrary shape of a potential field over the domain of input space. The authors also present a detailed learning algorithm for the GPFN. Learning consists of the determination of the minimally necessary number of GPFUs and the adjustment of the locations and shapes of the individual Gaussian potential fields defined by GPFUs as well as the summation weights. The learning of the minimally necessary number of GPFUs is based on the control of the effective radius of GPFUs, while the parameter learning is based on the gradient descent procedure.<<ETX>>