xnewgrnn.m

来自「《Matlab在化学工程中的应用》该书是我见过的一本相当有用的一本书 具有很高」· M 代码 · 共 36 行

function xNewgrnn
% xNewgrnn.m
%  函数逼近(function approximation)--用函数NEWGRNN()和SIM()创建和仿真
%  普遍化回归神经网络(generalized regression neural network,GRNN)
%
%   Author: HUANG Huajiang
%   Copyright 2003 UNILAB Research Center,
%   East China University of Science and Technology, Shanghai, PRC
%   $Revision: 1.0 $  $Date: 2003/01/12 $
%
%   [Ref] MATLAB demo, Mathworks Co.

clear all
clc

p = [1 2 3 4 5 6 7 8]; % inputs p
t = [0 1 2 3 2 1 2 1]; % target outputs t

spread = 0.7; % a smaller spread would fit data better but be less smooth.
net = newgrnn(p,t,spread); % 用NEWGRNN()一个普遍化回归神经网络
a = sim(net,p);

% 模拟计算网络对多个输入值的响应
cla reset
p2 = 0:.1:9;
a2 = sim(net,p2);
plot(p2,a2,'linewidth',3,'color',[1 0 0])
hold on
plot(p,t,'.','markersize',20)
axis([0 9 -1 4])
title('函数逼近')
xlabel('p 和 p2')
ylabel('t 和 a2')'