matlab如何获得神经网络次数

A. 找高手教我matlab的神经网络训练

% 运用比例共轭梯度动量算法来训练 BP网络
clear all;
pause(1);
P=[0.1452 0.1466 0.1314 0.2243 0.3523 0.4642 0.5015 0.6981 0.7821 0.8345 0.9649 1.156 0.2415 0.3027 0;
0.1217 0.1581 0.1408 0.2304 0.3143 0.4312 0.5819 0.7125 0.8065 0.8647 0.9726 1.132 0.2385 0.3125 0;
0.1525 0.1627 0.1507 0.2406 0.3502 0.4636 0.5051 0.7352 0.8459 0.8915 0.9654 1.156 0.2216 0.2701 1;
0.1016 0.1105 0.1234 0.1978 0.3021 0.4232 0.5819 0.6952 0.8015 0.8725 0.9825 1.095 0.2352 0.2506 0.5;
0.1115 0.1201 0.1312 0.2019 0.3532 0.4736 0.5029 0.7032 0.8189 0.8619 0.9365 1.125 0.2542 0.3125 0;
0.1335 0.1322 0.1534 0.2214 0.3623 0.4827 0.5198 0.7276 0.8359 0.8906 0.9592 1.143 0.2601 0.3198 0;
0.1368 0.1432 0. 0.2205 0.3823 0.4971 0.5136 0.7129 0.8263 0.8953 0.9891 1.137 0.2579 0.3099 0;
0.1342 0.1368 0.1602 0.2131 0.3726 0.4822 0.5101 0.7098 0.8127 0.8921 0.9995 1.126 0.2301 0.2867 0.5;
0.1113 0.1212 0.1305 0.1819 0.3952 0.4312 0.5886 0.6898 0.7999 0.8423 0.9721 1.095 0.2234 0.2799 1;
0.1005 0.1121 0.1207 0.1605 0.3556 0.4022 0.5553 0.6673 0.7798 0.8623 0.9521 1.087 0.2314 0.2977 0]';
T=[0.1217 0.1581 0.1408 0.2304 0.3143 0.4312 0.5819 0.7125 0.8265 0.8847 0.9826 1.132;
0.1525 0.1627 0.1507 0.2406 0.3502 0.4636 0.5051 0.7352 0.8459 0.8915 0.9464 1.156;
0.1016 0.1105 0.1234 0.1978 0.3021 0.4232 0.5819 0.6952 0.8015 0.8825 0.9825 1.102;
0.1115 0.1201 0.1312 0.2019 0.3532 0.4736 0.5029 0.7032 0.8189 0.8919 0.9965 1.125;
0.1335 0.1322 0.1534 0.2214 0.3623 0.4827 0.5198 0.7276 0.8359 0.8506 0.9892 1.123;
0.1368 0.1432 0. 0.2205 0.3823 0.4971 0.5136 0.7129 0.8263 0.8953 0.9691 1.117;
0.1342 0.1368 0.1602 0.2131 0.3726 0.4822 0.5101 0.7098 0.8127 0.8921 0.9995 1.126;
0.1113 0.1212 0.1305 0.1819 0.3952 0.4312 0.5886 0.6898 0.7999 0.8323 0.9721 1.156;
0.1005 0.1121 0.1207 0.1605 0.3556 0.4022 0.5553 0.6673 0.7798 0.8623 0.9521 1.156;
0.1123 0.1257 0.1343 0.2079 0.3579 0.4716 0.5459 0.7145 0.8205 0.8901 0.9419 1.136]';
threshold=[0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1;0 1];
net=newff(threshold,[32,12],{'tansig','logsig'},'trainscg','learngdm');%新建BP神经网络
net.trainParam.epochs=1000;%bp网络训练次数
net.trainParam.goal=0.002;%网络训练目标
net.trainParam.lr=0.01;%网络学习速率
[net,tr]=train(net,P,T);%训练网络
P_test=[0.1123 0.1257 0.1343 0.2079 0.3579 0.4716 0.5459 0.7145 0.8205 0.8901 0.9419 1.136 0.2317 0.2936 0]';%网络输入数据
Out=sim(net,P_test);%网络仿真
X=[0.1119 0.1215 0.1621 0.2161 0.3471 0.4639 0.5555 0.7061 0.8243 0.8923 0.9522 1.129];%实际测得数据
t=1:1:12;
box off;
grid off;
plot(t,Out,'b',t,X,'r');%画出二维图形
set(gca,'Xtick',0:1:24,'Ytick',0:.1:1.4);%设置坐标
title('基于BP网络的设备故障时间序列预测');
xlabel('时间/2小时');
ylabel('加速度/g');
text(1.5,1.2,'预测振动曲线(蓝）');
text(1.5,1.1,'实际测试曲线(红）');

B. matlab 神经网络

net=newff(pr,[3,2],{'logsig','logsig'}); %创建 一个bp 神经网络
net.trainParam.show = 10; %显示训练迭代过程
net.trainParam.lr = 0.05; %学习速率0,05
net.trainParam.goal = 1e-10; %训练精度
net.trainParam.epochs = 50000; %最大训练次数
net = train(net,p,goal); %训练
结果要么接近于1 ，要么就是0，就这俩类啊，这就是分类结果；
每次都有些差异 很正常，只要不大

C. matlab中如何获取神经网络训练之后的迭代次数

多种方法途径可以获取，如训练后，运行以下语句：

nntraintool

--------------出现窗口中的Progress-epoch显示迭代次数

D. matlab中如何对newrb神经网络进行多次训练就是好几组输入输出数组对同一网络进行多次训练。求代码

[slot].name);printf("Enterstreet:");gets(addr_list[slot].street);printf("Entercity:");gets(addr_list[slot].city);printf("Enterstate:");gets(addr_list[slot].state);printf("Enterzip:");gets(s);addr_list[slot].zip=strtoul(s,'\0',10);}/*Findanunusedstructure.*/intfind_free(void){registerintt;for(t=0;addr_list[t].name[0]&&t=0&&slot

E. MATLAB线性神经网络的程序，跪求。。

美国Michigan 大学的 Holland 教授提出的遗传算法(GeneticAlgorithm, GA)是求解复杂的组合优化问题的有效方法 ，其思想来自于达尔文进化论和门德尔松遗传学说 ，它模拟生物进化过程来从庞大的搜索空间中筛选出较优秀的解，是一种高效而且具有强鲁棒性方法。所以，遗传算法在求解TSP和 MTSP问题中得到了广泛的应用。

matlab程序如下：

function[opt_rte,opt_brk,min_dist] =mtspf_ga(xy,dmat,salesmen,min_tour,pop_size,num_iter)

%%

%实例

% n = 20;%城市个数

% xy = 10*rand(n,2);%城市坐标 随机产生，也可以自己设定

% salesmen = 5;%旅行商个数

% min_tour = 3;%每个旅行商最少访问的城市数

% pop_size = 80;%种群个数

% num_iter = 200;%迭代次数

% a = meshgrid(1:n);

% dmat =reshape(sqrt(sum((xy(a,:)-xy(a',:)).^2,2)),n,n);

% [opt_rte,opt_brk,min_dist] = mtspf_ga(xy,dmat,salesmen,min_tour,...

% pop_size,num_iter);%函数

%%

[N,dims]= size(xy); %城市矩阵大小

[nr,nc]= size(dmat); %城市距离矩阵大小

n = N -1;% 除去起始的城市后剩余的城市的数

% 初始化路线、断点的选择

num_brks= salesmen-1;

dof = n- min_tour*salesmen; %初始化路线、断点的选择

addto =ones(1,dof+1);

for k =2:num_brks

addto = cumsum(addto);

end

cum_prob= cumsum(addto)/sum(addto);

%% 初始化种群

pop_rte= zeros(pop_size,n); % 种群路径

pop_brk= zeros(pop_size,num_brks); % 断点集合的种群

for k =1:pop_size

pop_rte(k,:) = randperm(n)+1;

pop_brk(k,:) = randbreaks();

end

% 画图路径曲线颜色

clr =[1 0 0; 0 0 1; 0.67 0 1; 0 1 0; 1 0.5 0];

ifsalesmen > 5

clr = hsv(salesmen);

end

%%

% 基于遗传算法的MTSP

global_min= Inf; %初始化最短路径

total_dist= zeros(1,pop_size);

dist_history= zeros(1,num_iter);

tmp_pop_rte= zeros(8,n);%当前的路径设置

tmp_pop_brk= zeros(8,num_brks); %当前的断点设置

new_pop_rte= zeros(pop_size,n);%更新的路径设置

new_pop_brk= zeros(pop_size,num_brks);%更新的断点设置

foriter = 1:num_iter

% 计算适应值

for p = 1:pop_size

d = 0;

p_rte = pop_rte(p,:);

p_brk = pop_brk(p,:);

rng = [[1 p_brk+1];[p_brk n]]';

for s = 1:salesmen

d = d + dmat(1,p_rte(rng(s,1)));% 添加开始的路径

for k = rng(s,1):rng(s,2)-1

d = d + dmat(p_rte(k),p_rte(k+1));

end

d = d + dmat(p_rte(rng(s,2)),1); % 添加结束的的路径

end

total_dist(p) = d;

end

% 找到种群中最优路径

[min_dist,index] = min(total_dist);

dist_history(iter) = min_dist;

if min_dist < global_min

global_min = min_dist;

opt_rte = pop_rte(index,:); %最优的最短路径

opt_brk = pop_brk(index,:);%最优的断点设置

rng = [[1 opt_brk+1];[opt_brk n]]';%设置记录断点的方法

figure(1);

for s = 1:salesmen

rte = [1 opt_rte(rng(s,1):rng(s,2))1];

plot(xy(rte,1),xy(rte,2),'.-','Color',clr(s,:));

title(sprintf('城市数目为 = %d,旅行商数目为 = %d,总路程 = %1.4f, 迭代次数 =%d',n+1,salesmen,min_dist,iter));

hold on

grid on

end

plot(xy(1,1),xy(1,2),'ko');

hold off

end

% 遗传操作

rand_grouping = randperm(pop_size);

for p = 8:8:pop_size

rtes = pop_rte(rand_grouping(p-7:p),:);

brks = pop_brk(rand_grouping(p-7:p),:);

dists =total_dist(rand_grouping(p-7:p));

[ignore,idx] = min(dists);

best_of_8_rte = rtes(idx,:);

best_of_8_brk = brks(idx,:);

rte_ins_pts = sort(ceil(n*rand(1,2)));

I = rte_ins_pts(1);

J = rte_ins_pts(2);

for k = 1:8 %产生新种群

tmp_pop_rte(k,:) = best_of_8_rte;

tmp_pop_brk(k,:) = best_of_8_brk;

switch k

case 2% 倒置操作

tmp_pop_rte(k,I:J) =fliplr(tmp_pop_rte(k,I:J));

case 3 % 互换操作

tmp_pop_rte(k,[I J]) =tmp_pop_rte(k,[J I]);

case 4 % 滑动平移操作

tmp_pop_rte(k,I:J) =tmp_pop_rte(k,[I+1:J I]);

case 5% 更新断点

tmp_pop_brk(k,:) = randbreaks();

case 6 % 倒置并更新断点

tmp_pop_rte(k,I:J) =fliplr(tmp_pop_rte(k,I:J));

tmp_pop_brk(k,:) =randbreaks();

case 7 % 互换并更新断点

tmp_pop_rte(k,[I J]) =tmp_pop_rte(k,[J I]);

tmp_pop_brk(k,:) =randbreaks();

case 8 % 评议并更新断点

tmp_pop_rte(k,I:J) =tmp_pop_rte(k,[I+1:J I]);

tmp_pop_brk(k,:) =randbreaks();

otherwise

end

end

new_pop_rte(p-7:p,:) = tmp_pop_rte;

new_pop_brk(p-7:p,:) = tmp_pop_brk;

end

pop_rte = new_pop_rte;

pop_brk = new_pop_brk;

end

figure(2)

plot(dist_history,'b','LineWidth',2);

title('历史最优解');

xlabel('迭代次数')

ylabel('最优路程')

% 随机产生一套断点 的集合

function breaks = randbreaks()

if min_tour == 1 % 一个旅行商时，没有断点的设置

tmp_brks = randperm(n-1);

breaks =sort(tmp_brks(1:num_brks));

else % 强制断点至少找到最短的履行长度

num_adjust = find(rand <cum_prob,1)-1;

spaces =ceil(num_brks*rand(1,num_adjust));

adjust = zeros(1,num_brks);

for kk = 1:num_brks

adjust(kk) = sum(spaces == kk);

end

breaks = min_tour*(1:num_brks) +cumsum(adjust);

end

end

disp('最优路径为：/n')

disp(opt_rte);

disp('其中断点为为：/n')

disp(opt_brk);

end