matlab如何獲得神經網路次數

A. 找高手教我matlab的神經網路訓練

% 運用比例共軛梯度動量演算法來訓練 BP網路
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神經網路
net.trainParam.epochs=1000;%bp網路訓練次數
net.trainParam.goal=0.002;%網路訓練目標
net.trainParam.lr=0.01;%網路學習速率
[net,tr]=train(net,P,T);%訓練網路
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]';%網路輸入數據
Out=sim(net,P_test);%網路模擬
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];%實際測得數據
t=1:1:12;
box off;
grid off;
plot(t,Out,'b',t,X,'r');%畫出二維圖形
set(gca,'Xtick',0:1:24,'Ytick',0:.1:1.4);%設置坐標
title('基於BP網路的設備故障時間序列預測');
xlabel('時間/2小時');
ylabel('加速度/g');
text(1.5,1.2,'預測振動曲線(藍）');
text(1.5,1.1,'實際測試曲線(紅）');

B. matlab 神經網路

net=newff(pr,[3,2],{'logsig','logsig'}); %創建 一個bp 神經網路
net.trainParam.show = 10; %顯示訓練迭代過程
net.trainParam.lr = 0.05; %學習速率0,05
net.trainParam.goal = 1e-10; %訓練精度
net.trainParam.epochs = 50000; %最大訓練次數
net = train(net,p,goal); %訓練
結果要麼接近於1 ，要麼就是0，就這倆類啊，這就是分類結果；
每次都有些差異 很正常，只要不大

C. matlab中如何獲取神經網路訓練之後的迭代次數

多種方法途徑可以獲取，如訓練後，運行以下語句：

nntraintool

--------------出現窗口中的Progress-epoch顯示迭代次數

D. matlab中如何對newrb神經網路進行多次訓練就是好幾組輸入輸出數組對同一網路進行多次訓練。求代碼

[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線性神經網路的程序，跪求。。

美國Michigan 大學的 Holland 教授提出的遺傳演算法(GeneticAlgorithm, GA)是求解復雜的組合優化問題的有效方法 ，其思想來自於達爾文進化論和門德爾松遺傳學說 ，它模擬生物進化過程來從龐大的搜索空間中篩選出較優秀的解，是一種高效而且具有強魯棒性方法。所以，遺傳演算法在求解TSP和 MTSP問題中得到了廣泛的應用。

matlab程序如下：

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

%%

%實例

% n = 20;%城市個數

% xy = 10*rand(n,2);%城市坐標 隨機產生，也可以自己設定

% salesmen = 5;%旅行商個數

% min_tour = 3;%每個旅行商最少訪問的城市數

% pop_size = 80;%種群個數

% num_iter = 200;%迭代次數

% 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);%函數

%%

[N,dims]= size(xy); %城市矩陣大小

[nr,nc]= size(dmat); %城市距離矩陣大小

n = N -1;% 除去起始的城市後剩餘的城市的數

% 初始化路線、斷點的選擇

num_brks= salesmen-1;

dof = n- min_tour*salesmen; %初始化路線、斷點的選擇

addto =ones(1,dof+1);

for k =2:num_brks

addto = cumsum(addto);

end

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

%% 初始化種群

pop_rte= zeros(pop_size,n); % 種群路徑

pop_brk= zeros(pop_size,num_brks); % 斷點集合的種群

for k =1:pop_size

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

pop_brk(k,:) = randbreaks();

end

% 畫圖路徑曲線顏色

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

ifsalesmen > 5

clr = hsv(salesmen);

end

%%

% 基於遺傳演算法的MTSP

global_min= Inf; %初始化最短路徑

total_dist= zeros(1,pop_size);

dist_history= zeros(1,num_iter);

tmp_pop_rte= zeros(8,n);%當前的路徑設置

tmp_pop_brk= zeros(8,num_brks); %當前的斷點設置

new_pop_rte= zeros(pop_size,n);%更新的路徑設置

new_pop_brk= zeros(pop_size,num_brks);%更新的斷點設置

foriter = 1:num_iter

% 計算適應值

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)));% 添加開始的路徑

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); % 添加結束的的路徑

end

total_dist(p) = d;

end

% 找到種群中最優路徑

[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,:); %最優的最短路徑

opt_brk = pop_brk(index,:);%最優的斷點設置

rng = [[1 opt_brk+1];[opt_brk n]]';%設置記錄斷點的方法

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('城市數目為 = %d,旅行商數目為 = %d,總路程 = %1.4f, 迭代次數 =%d',n+1,salesmen,min_dist,iter));

hold on

grid on

end

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

hold off

end

% 遺傳操作

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 %產生新種群

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 % 互換操作

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

case 4 % 滑動平移操作

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

case 5% 更新斷點

tmp_pop_brk(k,:) = randbreaks();

case 6 % 倒置並更新斷點

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

tmp_pop_brk(k,:) =randbreaks();

case 7 % 互換並更新斷點

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

tmp_pop_brk(k,:) =randbreaks();

case 8 % 評議並更新斷點

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('歷史最優解');

xlabel('迭代次數')

ylabel('最優路程')

% 隨機產生一套斷點 的集合

function breaks = randbreaks()

if min_tour == 1 % 一個旅行商時，沒有斷點的設置

tmp_brks = randperm(n-1);

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

else % 強制斷點至少找到最短的履行長度

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('最優路徑為：/n')

disp(opt_rte);

disp('其中斷點為為：/n')

disp(opt_brk);

end