An analytical framework for local feedforward networks
An analytical framework for local feedforward networks
复制标题
局部前馈网络的分析框架
DOI：
10.1109/isic.1996.556243
复制
发表时间：
1996
期刊：
影响因子：
--
通讯作者：
M. Polycarpou
中科院分区：
文献类型：
--
作者：
S. Weaver;L. Baird;M. Polycarpou
虽然前馈神经网络非常适合于函数逼近，但在某些应用中，网络在学习期望函数时会遇到问题。一个问题是干扰，当在输入空间的一个区域学习导致在另一个区域忘记学习时发生的干扰。不易受干扰影响的网络称为空间本地网络。为了理解这些特性，开发了一个理论框架，该框架包括干扰度量和网络局部化度量，该框架不仅包含网络权重和体系结构，还包含学习算法。利用这个框架分析了采用Back-Prop学习算法的Sigmoid多层感知器(MLP)网络，通过证明在给定足够多的可调参数的情况下，Sigmoid型多层感知器(MLP)可以成为任意局部的，同时保持了表示紧致域上的任何连续函数的能力，从而解决了Sigmoid型网络固有的非局部性的常见误解。
Although feedforward neural networks are well suited to function approximation, in some applications networks experience problems when learning a desired function. One problem is interference which occurs when learning in one area of the input space causes unlearning in another area. Networks that are less susceptible to interference are referred to as spatially local networks. To understand these properties, a theoretical framework, consisting of a measure of interference and a measure of network localization, is developed that incorporates not only the network weights and architecture but also the learning algorithm. Using this framework to analyze sigmoidal multi-layer perceptron (MLP) networks that employ the back-prop learning algorithm, we address a familiar misconception that sigmoidal networks are inherently non-local by demonstrating that given a sufficiently large number of adjustable parameters, sigmoidal MLPs can be made arbitrarily local while retaining the ability to represent any continuous function on a compact domain.