Toddickme的博客

原创 随机梯度下降

x_data = [1.0, 2.0, 3.0]y_data = [2.0, 4.0, 6.0]w = 1.0def forward(x): return x * wdef loss(x, y): y_pred = forward (x) return (y_pred - y) ** 2def gradient(x, y): return 2 * x * y * (x * w - y)print ('Predict(before training.

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 Categoricaldevice = paddle.get_device()env = gym.make("CartPole-v0") s.

原创 paddlepaddle图片采样

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 PCA学习

import numpy as npmat = np.array([[2.5, 2.4], [0.5, 0.7], [2.2, 2.9], [1.9, 2.2], [3.1, 3], [2.3, 2.7], [2, 1.6], [1, 1.1], [.

原创 推导

原创 欧拉公式学习

import matplotlib.pyplot as pltdef euler1(): x = 0 y = 1 for i in range(100): y = 1.1 * y - 0.2 * x / y x = x + 0.1 lx.append(x) ly.append(y) return lx,lylx = []ly = []euler1()fig = plt.figure()ax = .

原创 神经网络学习

import numpy as np# func neuron:sigmoid函数，也就是作为激活函数，模拟神经元的阈值兴奋反应 deriv导数def neuron(x, deriv=False): if deriv: return x * (1 - x) return 1 / (1 + np.exp(-x))# 输入数据x = np.array([[0, 0, 1], [1, 1, 1], [1, .

原创 numpy的应用及结果

import numpy as np# numpy基本加减和取行操作a = np.array([1,1,1,1])b = np.array([[1],[1],[1],[1]])c = np.array([[1,1,1,1]])t1=a+bt2=c+bprint(t1)print(t2,'\n') # 广播机制W = np.array([[1,1,1],[2,2,2]])print(W[:,1]) # 会返回一维数组print(W[1],'\n') # 取得是W1行，返回的也是一维..

原创 2021-09-03

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