- 确定各层神经元个数;
- 初始化参数;
- 前向传播,求神经网络的输出值;
- 计算cost;
- 后向传播,求各参数的偏导数值;
- 更新各参数值(使用偏导数、学习效率alpha),完成一次迭代;
- 达到迭代次数,确定神经网络的最终参数;
- 使用参数修正的神经网络预测样本;
- 求准确率。
1、前向传播和后向传播
compute the cost J as follows:
J
=
−
1
m
∑
i
=
0
m
(
y
(
i
)
log
(
a
[
2
]
(
i
)
)
+
(
1
−
y
(
i
)
)
log
(
1
−
a
[
2
]
(
i
)
)
)
(1)
J = - \frac{1}{m} \sum\limits_{i = 0}^{m} \large{(} \small y^{(i)}\log\left(a^{[2] (i)}\right) + (1-y^{(i)})\log\left(1- a^{[2] (i)}\right) \large{)} \small\tag{1}
J=−m1i=0∑m(y(i)log(a[2](i))+(1−y(i))log(1−a[2](i)))(1)
对于式(1):
1.1 前向传播代码(forward_propagation)
def forward_propagation_n(X, Y, parameters):
"""
Implements the forward propagation (and computes the cost) presented in Figure 3.
Arguments:
X -- training set for m examples
Y -- labels for m examples
parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3":
W1 -- weight matrix of shape (5, 4)
b1 -- bias vector of shape (5, 1)
W2 -- weight matrix of shape (3, 5)
b2 -- bias vector of shape (3, 1)
W3 -- weight matrix of shape (1, 3)
b3 -- bias vector of shape (1, 1)
Returns:
cost -- the cost function (logistic cost for one example)
"""
# retrieve parameters
m = X.shape[1]
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
W3 = parameters["W3"]
b3 = parameters["b3"]
# LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SIGMOID
Z1 = np.dot(W1, X) + b1
A1 = relu(Z1)
Z2 = np.dot(W2, A1) + b2
A2 = relu(Z2)
Z3 = np.dot(W3, A2) + b3
A3 = sigmoid(Z3)
# Cost
logprobs = np.multiply(-np.log(A3),Y) + np.multiply(-np.log(1 - A3), 1 - Y)
cost = 1./m * np.sum(logprobs)
cache = (Z1, A1, W1, b1, Z2, A2, W2, b2, Z3, A3, W3, b3)
return cost, cache
1.2 后向传播代码(backward_propagation):
# GRADED FUNCTION: backward_propagation
def backward_propagation(parameters, cache, X, Y):
"""
Implement the backward propagation using the instructions above.
Arguments:
parameters -- python dictionary containing our parameters
cache -- a dictionary containing "Z1", "A1", "Z2" and "A2".
X -- input data of shape (2, number of examples)
Y -- "true" labels vector of shape (1, number of examples)
Returns:
grads -- python dictionary containing your gradients with respect to different parameters
"""
m = X.shape[1]
# First, retrieve W1 and W2 from the dictionary "parameters".
### START CODE HERE ### (≈ 2 lines of code)
W1 =
# Retrieve also A1 and A2 from dictionary "cache".
### START CODE HERE ### (≈ 2 lines of code)
A1 = cache["A1"]
A2 = cache["A2"]
### END CODE HERE ###
# Backward propagation: calculate dW1, db1, dW2, db2.
### START CODE HERE ### (≈ 6 lines of code, corresponding to 6 equations on slide above)
dZ2 = A2 - Y
dW2 = np.dot(dZ2, A1.T)/m
db2 = np.sum(dZ2, axis=1, keepdims=True)/m
dZ1 = np.dot(W2.T, dZ2)*(1-np.power(A1, 2))
dW1 = np.dot(dZ1, X.T)/m
db1 = np.sum(dZ1, axis=1, keepdims=True)/m
### END CODE HERE ###
grads = {"dW1": dW1,
"db1": db1,
"dW2": dW2,
"db2": db2}
return grads
2、Add L2 regularization
The standard way to avoid overfitting is called L2 regularization. from:
J
=
−
1
m
∑
i
=
1
m
(
y
(
i
)
log
(
a
[
L
]
(
i
)
)
+
(
1
−
y
(
i
)
)
log
(
1
−
a
[
L
]
(
i
)
)
)
(2)
J = -\frac{1}{m} \sum\limits_{i = 1}^{m} \large{(}\small y^{(i)}\log\left(a^{[L](i)}\right) + (1-y^{(i)})\log\left(1- a^{[L](i)}\right) \large{)} \tag{2}
J=−m1i=1∑m(y(i)log(a[L](i))+(1−y(i))log(1−a[L](i)))(2)
To:
J
r
e
g
u
l
a
r
i
z
e
d
=
−
1
m
∑
i
=
1
m
(
y
(
i
)
log
(
a
[
L
]
(
i
)
)
+
(
1
−
y
(
i
)
)
log
(
1
−
a
[
L
]
(
i
)
)
)
⏟
cross-entropy cost
+
1
m
λ
2
∑
l
∑
k
∑
j
W
k
,
j
[
l
]
2
⏟
L2 regularization cost
(3)
J_{regularized} = \small \underbrace{-\frac{1}{m} \sum\limits_{i = 1}^{m} \large{(}\small y^{(i)}\log\left(a^{[L](i)}\right) + (1-y^{(i)})\log\left(1- a^{[L](i)}\right) \large{)} }_\text{cross-entropy cost} + \underbrace{\frac{1}{m} \frac{\lambda}{2} \sum\limits_l\sum\limits_k\sum\limits_j W_{k,j}^{[l]2} }_\text{L2 regularization cost} \tag{3}
Jregularized=cross-entropy cost
−m1i=1∑m(y(i)log(a[L](i))+(1−y(i))log(1−a[L](i)))+L2 regularization cost
m12λl∑k∑j∑Wk,j[l]2(3)
对于式(3),要对L2 regularization cost 求导
For each, you have to add the regularization term’s gradient (
d
d
W
(
1
2
λ
m
W
2
)
=
λ
m
W
\frac{d}{dW} ( \frac{1} {2}\frac{\lambda}{m} W^2) = \frac{\lambda}{m} W
dWd(21mλW2)=mλW).
所以有以下代码:
2.1 backward_propagation_with_regularization:
# GRADED FUNCTION: backward_propagation_with_regularization
def backward_propagation_with_regularization(X, Y, cache, lambd):
"""
Implements the backward propagation of our baseline model to which we added an L2 regularization.
Arguments:
X -- input dataset, of shape (input size, number of examples)
Y -- "true" labels vector, of shape (output size, number of examples)
cache -- cache output from forward_propagation()
lambd -- regularization hyperparameter, scalar
Returns:
gradients -- A dictionary with the gradients with respect to each parameter, activation and pre-activation variables
"""
m = X.shape[1]
(Z1, A1, W1, b1, Z2, A2, W2, b2, Z3, A3, W3, b3) = cache
dZ3 = A3 - Y
### START CODE HERE ### (approx. 1 line)
dW3 = 1./m * np.dot(dZ3, A2.T) + (lambd/m)* W3
### END CODE HERE ###
db3 = 1./m * np.sum(dZ3, axis=1, keepdims = True)
dA2 = np.dot(W3.T, dZ3)
dZ2 = np.multiply(dA2, np.int64(A2 > 0))
### START CODE HERE ### (approx. 1 line)
dW2 = 1./m * np.dot(dZ2, A1.T) + (lambd/m)* W2
### END CODE HERE ###
db2 = 1./m * np.sum(dZ2, axis=1, keepdims = True)
dA1 = np.dot(W2.T, dZ2)
dZ1 = np.multiply(dA1, np.int64(A1 > 0))
### START CODE HERE ### (approx. 1 line)
dW1 = 1./m * np.dot(dZ1, X.T) + (lambd/m)* W1
### END CODE HERE ###
db1 = 1./m * np.sum(dZ1, axis=1, keepdims = True)
gradients = {"dZ3": dZ3, "dW3": dW3, "db3": db3,"dA2": dA2,
"dZ2": dZ2, "dW2": dW2, "db2": db2, "dA1": dA1,
"dZ1": dZ1, "dW1": dW1, "db1": db1}
return gradients
3、dropout
dropout 为该网络每一层的神经元设定一个失活(drop)概率,(保留概率 keep-prob),在神经网络训练过程中,我们会丢弃一些神经元节点,在网络图上则表示为该神经元节点的进出连线被删除。最后我们会得到一个神经元更少、模型相对简单的神经网络,这样一来原先的过拟合情况就会大大的得到缓解。
因为 dropout 可以随时随机的丢弃任何一个神经元,神经网络的训练结果不会依赖于任何一个输入特征,每一个神经元都以这种方式进行传播,并为神经元的所有输入增加一点权重,dropout 通过传播所有权重产生类似于 L2 正则化收缩权重的平方范数的效果,这样的权重压缩类似于 L2 正则化的权值衰减,这种外层的正则化起到了防止过拟合的作用。
另一个dropout有效的直观理解是,因为对于某个单元,输入单元有可能被删除,所以神经网络不会分配太大的权重,这相当于L2正则中的收缩权重的效果,所以说dropout的功能类似于L2正则。
所以说,总体而言,dropout 的功能类似于 L2 正则化,但又有所区别。另外需要注意的一点是,对于一个多层的神经网络,我们的 dropout 某层神经元的概率并不是一刀切的。
对于不同神经元个数的神经网络层,我们可以设置不同的失活或者保留概率,
对于单元数多、容易过拟合的层、含有较多权值的层,我们可以选择设置较大的失活概率(即较小的保留概率keep-prob)。
对于不容易过拟合可以用大一点的keep-prob。
所以,总结来说就是如果你担心某些层所含神经元较多或者比其他层更容易发生过拟合,我们可以将该层的失活概率设置的更高一些。
dropout的一大缺点就是:代价函数不再被明确定义,每次迭代都会随机移除一些节点,很难调试梯度下降的迭代过程(绘制迭代次数和cost的函数图)。
- 对于模型的某一层,设定一个概率keep-prob表示保留单元的概率。生成一个随机矩阵,表示每个样本和每个隐藏单元是否丢弃(1:丢弃;0:不丢弃):
D1 = np.random.rand(A1.shape[0], A1.shape[1]) # Step 1: initialize matrix D1 = np.random.rand(..., ...)
D1 = D1 < keep_prob # Step 2: convert entries of D1 to 0 or 1 (using keep_prob as the threshold)
# D1 = np.where(D1 <= keep_prob, 1, 0)
- 过滤掉D[1]中所有等于0的元素
A1 = A1 * D1 # Step 3: shut down some neurons of A1
- 后需要把所有数值除以这个保留概率(为了保证A1的期望不变)
A1 = A1 / keep_prob # Step 4: scale the value of neurons that haven't been shut down
3.1 forward_propagation_with_ dropout
# GRADED FUNCTION: forward_propagation_with_dropout
def forward_propagation_with_dropout(X, parameters, keep_prob = 0.5):
"""
Implements the forward propagation: LINEAR -> RELU + DROPOUT -> LINEAR -> RELU + DROPOUT -> LINEAR -> SIGMOID.
Arguments:
X -- input dataset, of shape (2, number of examples)
parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3":
W1 -- weight matrix of shape (20, 2)
b1 -- bias vector of shape (20, 1)
W2 -- weight matrix of shape (3, 20)
b2 -- bias vector of shape (3, 1)
W3 -- weight matrix of shape (1, 3)
b3 -- bias vector of shape (1, 1)
keep_prob - probability of keeping a neuron active during drop-out, scalar
Returns:
A3 -- last activation value, output of the forward propagation, of shape (1,1)
cache -- tuple, information stored for computing the backward propagation
"""
np.random.seed(1)
# retrieve parameters
W1 = parameters["W1"]
b1 = parameters["b1"]
W2 = parameters["W2"]
b2 = parameters["b2"]
W3 = parameters["W3"]
b3 = parameters["b3"]
# LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SIGMOID
Z1 = np.dot(W1, X) + b1
A1 = relu(Z1)
### START CODE HERE ### (approx. 4 lines) # Steps 1-4 below correspond to the Steps 1-4 described above.
D1 = np.random.rand(A1.shape[0], A1.shape[1]) # Step 1: initialize matrix D1 = np.random.rand(..., ...)
D1 = D1 < keep_prob # Step 2: convert entries of D1 to 0 or 1 (using keep_prob as the threshold)
A1 = A1 * D1 # Step 3: shut down some neurons of A1
A1 = A1 / keep_prob # Step 4: scale the value of neurons that haven't been shut down
### END CODE HERE ###
Z2 = np.dot(W2, A1) + b2
A2 = relu(Z2)
### START CODE HERE ### (approx. 4 lines)
D2 = np.random.rand(A2.shape[0], A2.shape[1]) # Step 1: initialize matrix D2 = np.random.rand(..., ...)
D2 = D2 < keep_prob # Step 2: convert entries of D2 to 0 or 1 (using keep_prob as the threshold)
A2 = A2 * D2 # Step 3: shut down some neurons of A2
A2 = A2 / keep_prob # Step 4: scale the value of neurons that haven't been shut down
### END CODE HERE ###
Z3 = np.dot(W3, A2) + b3
A3 = sigmoid(Z3)
cache = (Z1, D1, A1, W1, b1, Z2, D2, A2, W2, b2, Z3, A3, W3, b3)
return A3, cache
3.2 backward_propagation_with_dropout
# GRADED FUNCTION: backward_propagation_with_dropout
def backward_propagation_with_dropout(X, Y, cache, keep_prob):
"""
Implements the backward propagation of our baseline model to which we added dropout.
Arguments:
X -- input dataset, of shape (2, number of examples)
Y -- "true" labels vector, of shape (output size, number of examples)
cache -- cache output from forward_propagation_with_dropout()
keep_prob - probability of keeping a neuron active during drop-out, scalar
Returns:
gradients -- A dictionary with the gradients with respect to each parameter, activation and pre-activation variables
"""
m = X.shape[1]
(Z1, D1, A1, W1, b1, Z2, D2, A2, W2, b2, Z3, A3, W3, b3) = cache
dZ3 = A3 - Y
dW3 = 1./m * np.dot(dZ3, A2.T)
db3 = 1./m * np.sum(dZ3, axis=1, keepdims = True)
dA2 = np.dot(W3.T, dZ3)
### START CODE HERE ### (≈ 2 lines of code)
dA2 = dA2 * D2 # Step 1: Apply mask D2 to shut down the same neurons as during the forward propagation
dA2 = dA2 / keep_prob # Step 2: Scale the value of neurons that haven't been shut down
### END CODE HERE ###
dZ2 = np.multiply(dA2, np.int64(A2 > 0))
dW2 = 1./m * np.dot(dZ2, A1.T)
db2 = 1./m * np.sum(dZ2, axis=1, keepdims = True)
dA1 = np.dot(W2.T, dZ2)
### START CODE HERE ### (≈ 2 lines of code)
dA1 = dA1 * D1 # Step 1: Apply mask D1 to shut down the same neurons as during the forward propagation
dA1 = dA1 / keep_prob # Step 2: Scale the value of neurons that haven't been shut down
### END CODE HERE ###
dZ1 = np.multiply(dA1, np.int64(A1 > 0))
dW1 = 1./m * np.dot(dZ1, X.T)
db1 = 1./m * np.sum(dZ1, axis=1, keepdims = True)
gradients = {"dZ3": dZ3, "dW3": dW3, "db3": db3,"dA2": dA2,
"dZ2": dZ2, "dW2": dW2, "db2": db2, "dA1": dA1,
"dZ1": dZ1, "dW1": dW1, "db1": db1}
return gradients