[{"createTime":1735734952000,"id":1,"img":"hwy_ms_500_252.jpeg","link":"https://activity.huaweicloud.com/cps.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=V1g3MDY4NTY=&utm_medium=cps&utm_campaign=201905","name":"华为云秒杀","status":9,"txt":"华为云38元秒杀","type":1,"updateTime":1735747411000,"userId":3},{"createTime":1736173885000,"id":2,"img":"txy_480_300.png","link":"https://cloud.tencent.com/act/cps/redirect?redirect=1077&cps_key=edb15096bfff75effaaa8c8bb66138bd&from=console","name":"腾讯云秒杀","status":9,"txt":"腾讯云限量秒杀","type":1,"updateTime":1736173885000,"userId":3},{"createTime":1736177492000,"id":3,"img":"aly_251_140.png","link":"https://www.aliyun.com/minisite/goods?userCode=pwp8kmv3","memo":"","name":"阿里云","status":9,"txt":"阿里云2折起","type":1,"updateTime":1736177492000,"userId":3},{"createTime":1735660800000,"id":4,"img":"vultr_560_300.png","link":"https://www.vultr.com/?ref=9603742-8H","name":"Vultr","status":9,"txt":"Vultr送$100","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":5,"img":"jdy_663_320.jpg","link":"https://3.cn/2ay1-e5t","name":"京东云","status":9,"txt":"京东云特惠专区","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":6,"img":"new_ads.png","link":"https://www.iodraw.com/ads","name":"发布广告","status":9,"txt":"发布广告","type":1,"updateTime":1735660800000,"userId":3},{"createTime":1735660800000,"id":7,"img":"yun_910_50.png","link":"https://activity.huaweicloud.com/discount_area_v5/index.html?fromacct=261f35b6-af54-4511-a2ca-910fa15905d1&utm_source=aXhpYW95YW5nOA===&utm_medium=cps&utm_campaign=201905","name":"底部","status":9,"txt":"高性能云服务器2折起","type":2,"updateTime":1735660800000,"userId":3}]
<>梯度下降法代码python实现 -有数据有图有真相
今天我们做了一个实验，通过生成多元回归数据进行梯度下降求解权重
*
生成一份线性数据 y = w 1 ∗ x 1 = w 2 ∗ x 2 + w 3 ∗ x 3 + b y=w_1*x_1=w_2*x_2+w_3*x_3+b
y=w1∗x1=w2∗x2+w3∗x3+b
代码测试为 y = 5 ∗ x 1 = w 2 ∗ 7 + 4 ∗ x 3 + 8 y=5*x_1=w_2*7+4*x_3+8 y=5∗x1=w2∗7
+4∗x3+8
*
为线性数据增加噪声值 y=y+np.random.randn()*1+8
*
之后通过梯度下降算法进行迭代，迭代次数5000轮
*
绘制误差和权重迭代曲线
下面代码对于学习而言是个非常好的例子，如有疑问，可以在博客留言询问
import numpy as np import os import matplotlib.pyplot as plt w=np.array([5,7,4]
) sample=np.random.randint(0,10,(100,3)) y=np.dot(sample,w) #print(sample)
#print(y) y=y+np.random.randn()*1+8 print(y) w_zz=np.array([1,1,1,1])
learn_rating=0.0001 p=0 w=[[1],[1],[1],[1]] loss=[] for i in range(5000): d=0 p=
0 loss_sum=np.array([]) for x in sample: sample_convert=np.append(x,1) #
print(sample_convert) # print(np.dot(sample_convert,w_zz)-y[p]) loss_sum=np.
append(loss_sum,(np.dot(sample_convert,w_zz)-y[p])**2) d=d+learn_rating*
sample_convert*(np.dot(sample_convert,w_zz)-y[p]) p=p+1 # print(w_zz) w_zz=w_zz-
d loss.append(loss_sum.mean()) print(loss_sum.mean()) for i in range(4): w[i].
append(w_zz[i]) print(w_zz) #print(w) plt.plot(w[0]) plt.plot(w[1]) plt.plot(w[2
]) plt.plot(w[3]) plt.legend(["w1","w2","w3","w4"]) plt.show() plt.plot(loss[500
:]) plt.show() os.system("pause")
截图过下图所示
误差曲线图
权重迭代曲线图：
数据我已经上传到我的资源，可以免费下载，文件名为BP神经网络
