qq_48513539的博客

原创 反向传播算法

import numpy as npimport matplotlib.pyplot as pltfrom sklearn import datasetsfrom sklearn.model_selection import train_test_splitX, y = datasets.make_moons(n_samples=1000, noise=0.2, random_state=100)X_train, X_test, y_train, y_test = train_test_spli

原创 马尔科夫链模型状态转移矩阵

import numpy as npmatrix = np.matrix([[0.9,0.075,0.025],[0.15,0.8,0.05],[0.25,0.25,0.5]], dtype=float)vector1 = np.matrix([[0.3,0.4,0.3]], dtype=float)for i in range(100): vector1 = vector1*matrix print ("Current round:" , i+1) print (vector

原创 随机梯度下降法

import numpy as npimport matplotlib.pyplot as pltimport mathimport randomtheta0=random.random()theta1=random.random()theta2=random.random()a=0.01x=np.array([[2104,3], [1600,3], [2400,3], [1416,2], [3

原创 LDA推导过程

原创 决策树推导2

原创 决策树推导1

在这里插入图片描述

原创 强化学习Actor Critic Method

import gym, osfrom itertools import countimport paddleimport paddle.nn as nnimport paddle.optimizer as optimimport paddle.nn.functional as Ffrom paddle.distribution import Categoricalprint(paddle.__version__)device = paddle.get_device()env = gym

原创 通过极简方案构建手写数字识别模型

import paddlefrom paddle.nn import Linearimport paddle.nn.functional as Fimport osimport numpy as npimport matplotlib.pyplot as plttrain_dataset = paddle.vision.datasets.MNIST(mode='train')train_data0 = np.array(train_dataset[0][0])train_label_0

原创 使用卷积神经网络进行图像分类

import paddleimport paddle.nn.functional as Ffrom paddle.vision.transforms import ToTensorimport numpy as npimport matplotlib.pyplot as pltprint(paddle.__version__)transform = ToTensor()cifar10_train = paddle.vision.datasets.Cifar10(mode='train',

原创 证明▽·(▽×A)=0

原创 主成分分析

import numpy as npimport matplotlib . pyplot as pltx0 = [2.5,0.5,2.2,1.9,3.1,2.3,2,1,1.5,1.1]average1 = np.mean(x0)print('x0的平均值是：{}'.format(average1))y0 = [2.4,0.7,2.9,2.2,3,2.7,1.6,1.1,1.6,0.9]average2 = np.mean(y0)print('y0的平均值是：{}'.format(ave

原创 主成分分析

import numpy as npx0 = [2.5,0.5,2.2,1.9,3.1,2.3,2,1,1.5,1.1]average1 = np.mean(x0)print('x0的平均值是：{}'.format(average1))y0 = [2.4,0.7,2.9,2.2,3,2.7,1.6,1.1,1.6,0.9]average2 = np.mean(y0)print('y0的平均值是：{}'.format(average2))x1=x0-average1y1=y0-aver

原创 隐马尔可夫——第二种解法

import numpy as nppath=[]h_state = ["rainy","sunny"]obs = [0,1,2] #walk shop clean#初始状态start_p= [0.6,0.4] #rain sunny# 转移概率 r-r r-s s-r s-strans_p = np.array([[0.7, 0.3], [0.4, 0.6]])# 发射概率 rain-walk rain-shop rain-c

原创 隐马尔可夫 第一种解法

#初始天气概率s1=0.4r1=0.6#walk的概率sw1=0.6rw1=0.1#转变概率s1s2=0.6s1r2=0.4r1s2=0.3r1r2=0.7#shop概率ss2=0.3rs2=0.4#转变概率s2s3=0.6s2r3=0.4r2s3=0.3r2r3=0.7#clean概率sc3=0.1rc3=0.5psss=s1*sw1*s1s2*ss2*s2s3*sc3 #sun sun sun 0.00259pssr=s1*sw1*s1s2*ss2*s.

原创 神经网络的草稿

咱们就是说 也不知道写了个啥 好像就是吧公式全都写上去了 先交个作业吧…有时间在更正一下… x1=1 x2=1 x3=1 t1=t2=1 w41=w42=w43=w51=w52=w53=w61=w62=w63=w71=w72=w73=1 w84=w85=w86=w87=w94=w95=w96=w97=1 n=0.1 a4=x1*w41+x2*w42+x3*w43 a5=x1*w51+x2*w52+x3*w53 a6

原创 欧拉函数（2）

import matplotlib . pyplot as pltimport numpy as npt=0.1x=0y=1x1=0y1=1xx=np.zeros(100)yy=np.zeros(100)xx1=np.zeros(100)yy1=np.zeros(100)for i in range(100): y1=t*(y1-2*x1/y1)+y1 x1=x1+t xx1[i]=x1 yy1[i]=y1 k=y-2*x/y

原创 全链接神经网络推导

原创 贝叶斯公式

原创 9.14欧拉函数

import matplotlib . pyplot as pltimport numpy as nph=0.1x=0y=1xx=np.zeros(100)yy=np.zeros(100)for i in range(100): y=h*(y-2*x/y)+y x=x+h xx[i]=x yy[i]=y print(xx[i],yy[i])plt.plot(xx, yy, ls='-', lw=2, label='ola', color='pink'.

原创 9.9作业

原创 感知器实现and算法

import numpy as npimport matplotlib.pyplot as pltimport mathimport randoma=0.1w1=0.8w2=0.6eps=0.1delta1=9delta2=9x1=np.array([0,0,1,1])x2=np.array([0,1,0,1])t=np.array([0,0,0,1])e=float(1.18)while delta1>=eps and delta2>=eps: for i

原创 随机梯度下降法 监督学习

import numpy as npimport matplotlib.pyplot as pltimport mathimport randomtheta0=random.random()theta1=random.random()theta2=random.random()a=0.01x1=np.array([2104,1600,2400,1416,3000])x2=np.array([3,3,3,2,4])t=np.array([400,330,369,232,540])eps=

原创 numpy作业2

import numpy as npa=np.array([1,1,1,1])b=np.array([[1],[1],[1],[1]])a+barray([[2, 2, 2, 2], [2, 2, 2, 2], [2, 2, 2, 2], [2, 2, 2, 2]])c=np.array([[1,1,1,1]])c+barray([[2, 2, 2, 2], [2, 2, 2, 2], [2, 2, 2,

原创 numpy作业1

import numpy as np c = np.arange(1,13).reshape(6,2)carray([[ 1, 2], [ 3, 4], [ 5, 6], [ 7, 8], [ 9, 10], [11, 12]])np.vsplit(c,3)[array([[1, 2], [3, 4]]), array([[5, 6], [7, 8]]), array([[