正则化可以有效避免过拟合。 其中L2正则化如下图所示
L2项，即把每一层的每一个权重W 求其平方和
使用np.sum(np.square(Wl)) 求即可
def compute_cost_with_regularization(A3, Y, parameters, lambd): """ Implement the cost function with L2 regularization. See formula (2) above. Arguments: A3 -- post-activation, output of forward propagation, of shape (output size, number of examples) Y -- "true" labels vector, of shape (output size, number of examples) parameters -- python dictionary containing parameters of the model Returns: cost - value of the regularized loss function (formula (2)) """ m = Y.shape[1] W1 = parameters["W1"] W2 = parameters["W2"] W3 = parameters["W3"] cross_entropy_cost = compute_cost(A3, Y) # This gives you the cross-entropy part of the cost ### START CODE HERE ### (approx. 1 line) L2_regularization_cost = lambd * (np.sum(np.square(W1))+np.sum(np.square(W2))+np.sum(np.square(W3)))/(2*m) ### END CODER HERE ### cost = cross_entropy_cost + L2_regularization_cost return cost
对每一项dW 加上正则项
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*W3/m ### 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 * W2/m ### 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 * W1/m ### 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利用Drop out 随机使某些神经元失效，防止过拟合。其numpy实现抽象步骤如下：
1.使用np.random.rand(Ax.shape[0],Ax.shape[1]) 构建一个随机初始化矩阵D，其维度与当前层的激活值A相同。其每个值都在0-1之间
2.设置一个keep_prob 表示保存神经元可能性。另D = (D < keep_prob) 得到一个只含Ture 和False的矩阵，代表具体某个神经元是否激活。
3.另A= A * D ，使某些神经元失效。然后令A=A/keep_prob 保持期望值
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 = np.multiply(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 = np.multiply(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
1.对dAx = dAx * Dx 对失效神经元的微分项也进行屏蔽
2.把得到的dAx = dAx/keep_prob 保持期望值
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
输入层和输出层不使用Drop out
