B站刘二大人课程笔记整理lecture03 梯度下降
课程网址
部分课件内容:
梯度下降的代码如下:
import numpy as np
import matplotlib.pyplot as plt
x_data = [1.0,2.0,3.0]
y_data = [2.0,4.0,6.0]
w = 1.0
def forward(x):
return x * w
def cost(xs,ys):
cost = 0.0
for x,y in zip(xs,ys):
y_pred = forward(x)
cost += (y_pred - y) ** 2
return cost / len(xs)
def gradient(xs,ys):
grad = 0
for x,y in zip(xs,ys):
grad += 2 * (x*w - y) * x
return grad / len(xs)
print('Predicted(before training)',4,forward(4))
for epoch in range(100):
cost_val = cost(x_data,y_data)
grad_val = gradient(x_data,y_data)
w = w - 0.01 * grad_val
print('Epoch:', epoch,'w:',w, 'Loss:', cost_val)
print('Predicted(after training)',4,forward(4))
随机梯度下降的代码如下:
import numpy as np
import matplotlib.pyplot as plt
x_data = [1.0,2.0,3.0]
y_data = [2.0,4.0,6.0]
w = 1.0
def forward(x):
return x * w
def loss(x,y):
y_pred = forward(x)
return (y_pred - y) ** 2
def gradient(x,y):
return 2 * (x*w - y) * x
print('Predicted(before training)',4,forward(4))
for epoch in range(100):
for x,y in zip(x_data,y_data):
grad = gradient(x,y)
w = w - 0.01 * grad
print("\tgrad:",x,y,grad)
l = loss(x,y)
print('Epoch:', epoch,'w:',w, 'Loss:', l)
print('Predicted(after training)',4,forward(4))