matlab神经网络编程

1. 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，是戚镇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

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

end

丛仔橡 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

%%BP算法
functionOut=bpnet(p,t,p_test)
%p,t为样本需要提前组织好
globalS1
net=newff(minmax(p),[S1,8],{'tansig','purelin'},'trainlm');%trainlm训练函数最有效
%net=newff(P,T,31,{'tansig','purelin'},'trainlm');%新版用法
net.trainParam.epochs=1000;
net.trainParam.goal=0.00001;
net.trainParam.lr=0.01;
net.trainParam.showWindow=false;%阻止训练窗口的弹出
net.trainParam.showCommandLine=false;%阻止训练窗口的弹出
net=train(net,p,t);
Out=sim(net,p_test);
end