神经网络超参之权重初始化的方法

权重初始化

1、Zeros initialization 

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

2、Random initialization

parameters['W' + str(l)] = np.random.randn(layers_dims[l], layers_dims[l-1])*0.01
parameters['b' + str(l)] = np.zeros([layers_dims[l],1])

3、He initialization

parameters['W' + str(l)] = np.random.randn(layers_dims[l], layers_dims[l-1]) * np.sqrt(2*1.0/layers_dims[l-1])
parameters['b' + str(l)] = np.zeros((layers_dims[l],1))