在Matlab中用前馈网络模拟默认模式网络？

通过以下网络，我获得了非常不同的培训效率

net = patternnet(hiddenLayerSize);

接下来呢

net = feedforwardnet(hiddenLayerSize, 'trainscg');
net.layers{1}.transferFcn = 'tansig';
net.layers{2}.transferFcn = 'softmax';
net.performFcn = 'crossentropy';

在相同的数据上

我在想网络应该是一样的

hiddenLayerSize = 10;

% pass 1, with patternnet
net = patternnet(hiddenLayerSize);

net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

[net,tr] = train(net,x,t);

y = net(x);
performance = perform(net,t,y);

fprintf('pass 1, patternnet, performance: %f\n', performance);
fprintf('num_epochs: %d, stop: %s\n', tr.num_epochs, tr.stop);

% pass 2, with feedforwardnet
net = feedforwardnet(hiddenLayerSize, 'trainscg');
net.layers{1}.transferFcn = 'tansig';
net.layers{2}.transferFcn = 'softmax';
net.performFcn = 'crossentropy';

net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

[net,tr] = train(net,x,t);

y = net(x);
performance = perform(net,t,y);

fprintf('pass 2, feedforwardnet, performance: %f\n', performance);
fprintf('num_epochs: %d, stop: %s\n', tr.num_epochs, tr.stop);

% pass 1, with patternnet
net = patternnet(hiddenLayerSize);

net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

[net,tr] = train(net,x,t);

y = net(x);
performance = perform(net,t,y);

fprintf('pass 3, patternnet, performance: %f\n', performance);
fprintf('num_epochs: %d, stop: %s\n', tr.num_epochs, tr.stop);

% pass 2, with feedforwardnet
net = feedforwardnet(hiddenLayerSize, 'trainscg');
net.layers{1}.transferFcn = 'tansig';
net.layers{2}.transferFcn = 'softmax';
net.performFcn = 'crossentropy';

net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

[net,tr] = train(net,x,t);

y = net(x);
performance = perform(net,t,y);

fprintf('pass 4, feedforwardnet, performance: %f\n', performance);
fprintf('num_epochs: %d, stop: %s\n', tr.num_epochs, tr.stop);

我忘了什么

更新

下面的代码演示了，网络行为的唯一性取决于网络创建函数

每种类型的网络运行两次。这不包括随机生成器问题或其他问题。数据是一样的

hiddenLayerSize = 10;

% pass 1, with patternnet
net = patternnet(hiddenLayerSize);

net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

[net,tr] = train(net,x,t);

y = net(x);
performance = perform(net,t,y);

fprintf('pass 1, patternnet, performance: %f\n', performance);
fprintf('num_epochs: %d, stop: %s\n', tr.num_epochs, tr.stop);

% pass 2, with feedforwardnet
net = feedforwardnet(hiddenLayerSize, 'trainscg');
net.layers{1}.transferFcn = 'tansig';
net.layers{2}.transferFcn = 'softmax';
net.performFcn = 'crossentropy';

net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

[net,tr] = train(net,x,t);

y = net(x);
performance = perform(net,t,y);

fprintf('pass 2, feedforwardnet, performance: %f\n', performance);
fprintf('num_epochs: %d, stop: %s\n', tr.num_epochs, tr.stop);

% pass 1, with patternnet
net = patternnet(hiddenLayerSize);

net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

[net,tr] = train(net,x,t);

y = net(x);
performance = perform(net,t,y);

fprintf('pass 3, patternnet, performance: %f\n', performance);
fprintf('num_epochs: %d, stop: %s\n', tr.num_epochs, tr.stop);

% pass 2, with feedforwardnet
net = feedforwardnet(hiddenLayerSize, 'trainscg');
net.layers{1}.transferFcn = 'tansig';
net.layers{2}.transferFcn = 'softmax';
net.performFcn = 'crossentropy';

net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;

[net,tr] = train(net,x,t);

y = net(x);
performance = perform(net,t,y);

fprintf('pass 4, feedforwardnet, performance: %f\n', performance);
fprintf('num_epochs: %d, stop: %s\n', tr.num_epochs, tr.stop);

产出如下：

pass 1, patternnet, performance: 0.116445
num_epochs: 353, stop: Validation stop.
pass 2, feedforwardnet, performance: 0.693561
num_epochs: 260, stop: Validation stop.
pass 3, patternnet, performance: 0.116445
num_epochs: 353, stop: Validation stop.
pass 4, feedforwardnet, performance: 0.693561
num_epochs: 260, stop: Validation stop.

---

通常情况下，网络并不是以完全相同的方式进行每项训练。这取决于三个（我的意思是我知道三个）原因：

神经网络的初始初始化

数据标准化

数据缩放
如果说（1），网络最初配置为随机权重，在一些小范围内具有不同的符号。例如，具有6个输入的神经元可以获得如下初始权重：0.1、-0.3、0.16、-0.23、0.015、-0.0005。这可能会带来一点点新的训练结果。若要说（2），若你们的标准化执行得很差，那个么学习算法会收敛到局部极小值，并且不能跳出它。同样的情况也适用于案例（3），如果您的数据需要缩放，而您没有做到这一点

---

看起来这两个不太一样：

>> net = patternnet(hiddenLayerSize);
>> net2 = feedforwardnet(hiddenLayerSize,'trainscg');
>> net.outputs{2}.processParams{2}

ans =

    ymin: 0
    ymax: 1

>> net2.outputs{2}.processParams{2}

ans =

    ymin: -1
    ymax: 1

net.outputs{2}.processFcns{2}

是

mapminmax

，因此我推测其中之一是重新调整其输出，以便更好地匹配实际数据的输出范围

作为将来的参考，您可以通过强制转换到struct来比较内部数据结构。所以我做了一些类似的事情

n = struct(net); n2 = struct(net2);
for fn=fieldnames(n)';
  if(~isequaln(n.(fn{1}),n2.(fn{1})))
    fprintf('fields %s differ\n', fn{1});
  end
end

---

帮助找出差异。

请查看我的更新。1-3不可能是一个原因，因为结果会在多次运行中重现：

patternnet

系统性能优于（显然）相同的

feedforwardnet

。因此，原因可能是（可能）我以不同的方式初始化

feedforwardnet

，问题是：有什么区别。和。feedforwardnet更具通用性，更适用于近似函数，而patternnet更适用于模式识别。如果您的任务数据更适合patternnet，则patternnet的性能会更好，如果您的任务数据更适合feedforwardnet，然后，前馈网络将执行得更好。

patternnet

调用

feedforwardnet

内部和两个输出

network

对象。问题是：两种创作方式的实际区别是什么。我试图通过设置适当的传输和性能函数来复制它，但显然失败了。问题是：我忘了做什么？数据是用于分类的，但这并不重要。两个调用的数据相同。目标是使

feedforwardnet

与

patternnet

的工作方式相同。