这些是我的神经网络实现所涉及的步骤。
- 随机初始化权重 (θ Theta)
- 实现前向传播
- 计算成本函数
- 实现反向传播以计算偏导数
- 使用梯度下降
def forward_prop(X, theta_list):
m = X.shape[0]
a_list = []
z_list = []
a_list.append(np.insert(X, 0, values=np.ones(m), axis=1))
idx = 0
for idx, thera in enumerate(theta_list):
z_list.append(a_list[idx] * (theta_list[idx].T))
if idx != (len(theta_list)-1):
a_list.append(np.insert(sigmoid(z_list[idx]), 0, values=np.ones(m), axis=1))
else:
a_list.append(sigmoid(z_list[idx]))
return a_list, z_list
def back_prop(params, input_size, hidden_layers, num_labels, X, y, regularization, regularize):
m = X.shape[0]
X = np.matrix(X)
y = np.matrix(y)
theta_list = []
startCount = 0
idx = 0
for idx, val in enumerate(hidden_layers):
if idx == 0:
startCount = val * (input_size + 1)
theta_list.append(np.matrix(np.reshape(params[:startCount], (val, (input_size + 1)))))
if idx != 0:
tempCount = startCount
startCount += (val * (hidden_layers[idx-1] + 1))
theta_list.append(np.matrix(np.reshape(params[tempCount:startCount], (val, (hidden_layers[idx-1] + 1)))))
if idx == (len(hidden_layers)-1):
theta_list.append(np.matrix(np.reshape(params[startCount:], (num_labels, (val + 1)))))
a_list, z_list= forward_prop(X, theta_list)
J = cost(X, y, a_list[len(a_list)-1], theta_list, regularization, regularize)
d_list = []
d_list.append(a_list[len(a_list)-1] - y)
idx = 0
while idx < (len(theta_list)-1):
d_temp = np.multiply(d_list[idx] * theta_list[len(a_list) - 2 - idx], sigmoid_gradient(a_list[len(a_list) - 2 - idx]))
d_list.append(d_temp[:,1:])
idx += 1
delta_list = []
for theta in theta_list:
delta_list.append(np.zeros(theta.shape))
for idx, delta in enumerate(delta_list):
delta_list[idx] = delta_list[idx] + ((d_list[len(d_list) - 1 -idx].T) * a_list[idx])
delta_list[idx] = delta_list[idx] / m
if regularize:
for idx, delta in enumerate(delta_list):
delta_list[idx][:, 1:] = delta_list[idx][:, 1:] + (theta_list[idx][:, 1:] * regularization)
grad_list = np.ravel(delta_list[0])
idx = 1
while idx < (len(delta_list)):
grad_list = np.concatenate((grad_list, np.ravel(delta_list[idx])), axis=None)
idx += 1
return J, grad_list
def cost(X, y, h, theta_list, regularization, regularize):
m = X.shape[0]
X = np.matrix(X)
y = np.matrix(y)
J = (np.multiply(-y, np.log(h)) - np.multiply((1 - y), np.log(1 - h))).sum() / m
if regularize:
regularization_value = 0.0
for theta in theta_list:
regularization_value += np.sum(np.power(theta[:, 1:], 2))
J += (float(regularization) / (2 * m)) * regularization_value
return J
Implementation