progresses的博客

LDA推导

决策树推导

强化学习——Actor Critic Method import gym, os from itertools import count import paddle import paddle.nn as nn import paddle.optimizer as optim import paddle.nn.functional as F from paddle.distribution import Categorical device = paddle.get_device() env = gym.

使用paddle实现手写数字识别 import paddle from paddle.nn import Linear import paddle.nn.functional as F import os import numpy as np import matplotlib.pyplot as plt from PIL import Image # 定义mnist数据识别网络结构，同房价预测网络 class MNIST(paddle.nn.Layer): def __init__(self)

卷积神经网络图像处理 import paddle import paddle.nn.functional as F from paddle.vision.transforms import ToTensor import numpy as np import matplotlib.pyplot as plt transform = ToTensor() cifar10_train = paddle.vision.datasets.Cifar10(mode='train',

主成分分析（PCA） import numpy as np import matplotlib.pyplot as plt data = np.matrix([[2.5,2.4],[0.5,0.7],[2.2,2.9],[1.9,2.2],[3.1,3.0], [2.3,2.7],[2,1.6],[1,1.1],[1.5,1.6],[1.1,0.9]]) average = np.mean(data,axis=0) data_adjust = np.zeros((10,

隐马尔科夫模型 推导 代码

Euler作业（新） import matplotlib.pyplot as plt import numpy as np class Euler(): """新、旧欧拉算法比较""" def __init__(self): self.x = 0.2 self.y = 0.8 self.list_x = [0,0.2,] self.list_y = [1,0.8,] self.h = 0.2 def

反向传播算法公式及推导 图1图2

用欧拉法解初值问题 import matplotlib.pyplot as plt x = 0 y = 1 xx = [0] yy = [1] h = 0.1 for i in range (1,100): y = 1.1*y - 0.2*x/y x = x + h xx.append(x) yy.append(y) for i in range(100): print('%-30s%-20s' %(xx[i],yy[i])) fig = plt.figure()

使用python实现感知器 from __future__ import print_function from functools import reduce class VectorOp(object): """ 实现向量计算操作 """ def dot(x, y): """ 计算两个向量x和y的内积 """ # 首先把x[x1,x2,x3...]和y[y1,y2,y3,...]按元素相乘

import numpy as np import matplotlib.pyplot as plt x = np.array([[2104,3],[1600,3],[2400,3],[1416,2],[3000,4]]) y = np.array([400,330,369,232,540]) alpha = 0.1 theta0 = np.random.random() theta1 = np.random.random() theta2 = np.random.random() theta = np.

#垂直拆分，水平拆分 c = np.arange(1,13).reshape(6,2)#np.reshape() print(c) print(np.vsplit(c,3))#np.vsplit(),垂直拆分 d = c.T print(d) print(np.hsplit(d,3))#np.hspilt()水平拆分 e = np.array([ [[11, 21], [12, 22], [13, 23]], [[14, 24],