1.11 神经网络的权重初始化(Weight Initialization for Deep Networks)

忽略了常数项b

w[l] = np.random.randn(n[l],n[l-1])*np.sqrt(1/n[l-1])
w[l] = np.random.randn(n[l],n[l-1])*np.sqrt(2/n[l-1])
w[l] = np.random.randn(n[l],n[l-1])*np.sqrt(2/(n[l-1] + n[l]))

Last updated