分類預測 | MATLAB實現DBN-SVM深度置信網絡結合支持向量機多輸入分類預測

預測效果

基本介紹

1.分類預測 | MATLAB實現DBN-SVM深度置信網絡結合支持向量機多輸入分類預測
2.代碼說明：要求于Matlab 2021版及以上版本。

程序設計

• 完整程序和數據獲取方式1：同等價值程序兌換；
• 完整程序和數據獲取方式2：私信博主回復 MATLAB實現DBN-SVM深度置信網絡結合支持向量機多輸入分類預測獲取。

%%  劃分訓練集和測試集
P_train = res(1: num_train_s, 1: f_)';
T_train = res(1: num_train_s, f_ + 1: end)';
M = size(P_train, 2);P_test = res(num_train_s + 1: end, 1: f_)';
T_test = res(num_train_s + 1: end, f_ + 1: end)';
N = size(P_test, 2);%%  數據歸一化
[p_train, ps_input] = mapminmax(P_train, 0, 1);
p_test = mapminmax('apply', P_test, ps_input);[t_train, ps_output] = mapminmax(T_train, 0, 1);
t_test = mapminmax('apply', T_test, ps_output);
dbn = dbnsetup(dbn, p_train, opts);     % 建立模型
dbn = dbntrain(dbn, p_train, opts);     % 訓練模型
%-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
%%  訓練權重移植，添加輸出層
nn = dbnunfoldtonn(dbn, num_class);%%  反向調整網絡
opts.numepochs          = 576;  % 反向微調次數
opts.batchsize          = M;            % 每次反向微調樣本數 需滿足：（M / batchsize = 整數）nn.activation_function  = 'sigm';       % 激活函數
nn.learningRate         = 2.9189;       % 學習率
nn.momentum             = 0.5;          % 動量參數
nn.scaling_learningRate = 1;            % 學習率的比例因子[nn, loss, accu] = nntrain(nn, p_train, t_train, opts);  % 訓練
%-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
%%  仿真預測 
T_sim1 = nnpredict(nn, p_train); 
T_sim2 = nnpredict(nn, p_test );%%  性能評價
error1 = sum((T_sim1' == T_train)) / M * 100 ;
error2 = sum((T_sim2' == T_test )) / N * 100 ;
https://blog.csdn.net/kjm13182345320/article/details/131174983
版權聲明：本文為CSDN博主「機器學習之心」的原創文章，遵循CC 4.0 BY-SA版權協議，轉載請附上原文出處鏈接及本聲明。
原文鏈接：https://blog.csdn.net/kjm13182345320/article/details/130462492

參考資料

[1] https://blog.csdn.net/kjm13182345320/article/details/129679476?spm=1001.2014.3001.5501
[2] https://blog.csdn.net/kjm13182345320/article/details/129659229?spm=1001.2014.3001.5501
[3] https://blog.csdn.net/kjm13182345320/article/details/129653829?spm=1001.2014.3001.5501