scikit learn如何实现输出层

Question

在scikit learn中，输出层有多少个神经元？如前所述here，您只能指定隐藏层大小及其神经元，而不能指定输出层，因此我不确定 scikit learn 如何实现输出层。
对只有一个神经元的输出层使用 softmax 激活函数是否有意义？

Answer 1

测试：

设置：

In [227]: %paste
clf = MLPClassifier()

m = 10**3
n = 64

df = pd.DataFrame(np.random.randint(100, size=(m, n))).add_prefix('x') \
       .assign(y=np.random.choice([-1,1], m))


X_train, X_test, y_train, y_test = \
    train_test_split(df.drop('y',1), df['y'], test_size=0.2, random_state=33)

clf.fit(X_train, y_train)
## -- End pasted text --
Out[227]:
MLPClassifier(activation='relu', alpha=0.0001, batch_size='auto', beta_1=0.9,
       beta_2=0.999, early_stopping=False, epsilon=1e-08,
       hidden_layer_sizes=(100,), learning_rate='constant',
       learning_rate_init=0.001, max_iter=200, momentum=0.9,
       nesterovs_momentum=True, power_t=0.5, random_state=None,
       shuffle=True, solver='adam', tol=0.0001, validation_fraction=0.1,
       verbose=False, warm_start=False)

输出数量：

In [229]: clf.n_outputs_
Out[229]: 1

层数：

In [228]: clf.n_layers_
Out[228]: 3

求解器的迭代次数运行:

In [230]: clf.n_iter_
Out[230]: 60

这里是 source code 的摘录，其中将选择输出层的激活函数：

    # Output for regression
    if not is_classifier(self):
        self.out_activation_ = 'identity'
    # Output for multi class
    elif self._label_binarizer.y_type_ == 'multiclass':
        self.out_activation_ = 'softmax'
    # Output for binary class and multi-label
    else:
        self.out_activation_ = 'logistic'

更新： MLPClassifier binarizes (in a one-vs-all fashion) labels internaly, so logistic regression should work well also with labels that are differ from [0,1]：

    if not incremental:
        self._label_binarizer = LabelBinarizer()
        self._label_binarizer.fit(y)
        self.classes_ = self._label_binarizer.classes_

scikit learn如何实现输出层

How scikit learn implements the output layer

machine-learning

neural-network

scikit-learn

softmax