用Python进行神经网络初始化、正则、优化

初始化：

def model(...initilalization = 'he'):

if intitialization == 'he':

parameters = initialize_parameters_he(layers_dims)

-------------------------------------------------

def initialize_parameters_he(layers_dims):

np.random.seed(3)

parameters = {}

L = len(layers_dims) - 1

for i in range(1, L+1):

parameters['W' + str(l)] = np.random.randn(layers_dims[l], layers_dims[l-1]) * np.sqrt(2. / layers_dims[l-1])

parameters['b' + str(l)] = np.zeros((layers_dims[l], 1))

return parameters

正则化：

def model(..., lambd = 0, keep_prob = 1):

...

for i in range(0, num_iterations):

if keep_prob == 1:

a3, cache = forward_propagation(X, parameters)

elif keep_prob < 1:

a3, cache = forward_propagation_with_dropout(X, parameters, keep_prob)

if lambd == 0:

cost = compute_cost(a3, Y)

else:

cost = compute_cost_with_regularization(a3, Y, parameters, lambd)

...

return parameters

----------------------------------------------------------

def compute_cost_with_regularization(A3, Y, parameters, lambd):

m = Y.shape[1]

W1 = parameters['W1']

W2 = parameters['W2']

W3 = parameters['W3']

cross_entropy_cost = compute _cost(A3, Y)

L2_regularization_cost = (np.sum(np.square(W1)) + np.sum(np.square(W2)) + np.sum(np.square(W3))) * lambd / 2 / m

cost = cross_entropy_cost + L2_regularization_cost

return cost

-----------------------------------------------------------

def backward_propagation_with_regularization(X, Y, cache, lambd):

m = X.shape[1]

(Z1, A1, W1, b1, Z2, A2, W2, b2, Z3, A3, W3, b3) = cache

dZ3 = A3 - Y

dW3 = 1. / m * np.dot(dZ3,  A2.T) + lambd / m * W3

db3 = 1. / m * np.sum(dZ3, axis=1, keepdims = True)

dA2 = np.dot(W3.T, dZ3)

dZ2