随机梯度下降算法

概述

• 随机梯度下降，和批量梯度下降原理类似，区别在于求梯度时没有用所有样本的数据，而是仅仅选取一个样本j来求梯度，更新公式为：
  

• 随机梯度下降法由于每次仅仅采用一个样本来迭代，训练速度很快

# -*- coding:utf-8 _*-
# @author:  Fu zihao
# @file: pre01.py
import numpy as np
import random

# 学习率
ALPHA = 0.001
# 允许的最大误差
ERROR = 0.01

X1 = np.array([2014, 1600, 2400, 1416, 3000]).reshape(5, 1)
X2 = np.array([3, 3, 3, 2, 4]).reshape(5, 1)
T = np.array([400, 330, 369, 232, 540]).reshape(5, 1)
st0 = 0.5
st1 = 0.5
st2 = 0.5
ST0 = np.array([0.5, 0.5, 0.5, 0.5, 0.5]).reshape(5, 1)


def DT(X1, X2, T, ST0, st1, st2):
    dt0 = ST0 + st1 * X1 + st2 * X2 - T
    print(dt0, "--------------------")
    dt1 = (ST0 + st1 * X1 + st2 * X2 - T) * X1
    dt2 = (ST0 + st1 * X1 + st2 * X2 - T) * X2
    result = np.hstack((dt0, dt1, dt2))
    return result


dt = DT(X1, X2, T, ST0, st1, st2)[0]
dt0 = dt[0]
dt1 = dt[1]
dt2 = dt[2]
print(dt)

while dt0 >= ERROR or dt1 >= ERROR or dt2 >= ERROR:
    i = random.randint(0, 4)
    st0 = st0 - ALPHA * dt0
    st1 = st1 - ALPHA * dt1
    st2 = st2 - ALPHA * dt2
    ST0N = np.array([st0, st0, st0, st0, st0]).reshape(5, 1)
    dt = DT(X1, X2, T, ST0N, st1, st2)[i]
    dt0 = dt[0]
    dt1 = dt[1]
    dt2 = dt[2]

print("-------------------end--------------------")
print(st0, st1, st2)