随机梯度下降法学习

以下代码是学习李宏毅老师的课程，数据集为神奇宝贝进化后的cp数据值。

# -*- coding: utf-8 -*-
"""
Created on Thu May 31 09:59:54 2018

@author: Administrator
"""

import numpy as np
import matplotlib.pyplot as plt

#给出训练数据
x_data=[328,333,328,207,226,25,179,60,208,606]
y_data=[640,633,619,393,428,27,193,66,226,1591]

x=np.arange(-200,-100,1) #bias
y=np.arange(-5,5,0.1)#weight
z=np.zeros((len(x),len(y)))#loss
X,Y=np.meshgrid(x,y)
#计算偏导
for i in range(len(x)):
    for j in range(len(y)):
        b=x[i]
        w=y[i]
        z[j][i]=0
        for n in range(len(x_data)):
            z[j][i]=z[i][j]+(y_data[n]-b-w*x_data[n])**2
        z[j][i]=z[j][i]/len(x_data)



b=-120 #初始化b
w=-4 #初始化w
lr=0.000001#学习率
iteration=1000000

#存储初始值
b_history=[b]
w_history=[w]

lr_b=0
lr_w=0

#进行迭代
for i in range(iteration):
    b_grad=0.0
    w_grad=0.0
    for n in range(len(x_data)):
        b_grad=b_grad-2*(y_data[n]-b-w*x_data[n])*1
        w_grad=w_grad-2*(y_data[n]-b-w*x_data[n])*x_data[n]
    
    lr_b=lr/np.sqrt(lr_b)+b_grad
    lr_w=lr/np.sqrt(lr_w)+w_grad
    
    #更新参数
    b=b-lr*b_grad
    w=w-lr*w_grad
    #参数存储
    b_history.append(b)
    w_history.append(w)
    
#做出图像
plt.contourf(x,y,z,50,alpha=0.5,cmap=plt.get_cmap('jet'))
plt.plot([-188.4],[2.67],'x',ms=12,markeredgewidth=3,color='orange')
plt.plot(b_history,w_history,'o-',ms=3,lw=1.5,color='black')
plt.xlim(-200,-100)
plt.ylim(-5,5)
plt.xlabel(r'$b$',fontsize=16)
plt.ylabel(r'$b$',fontsize=16)
plt.show()

训练结果收敛：