B1gboss的博客

原创 随机梯度下降法

import numpy as npimport matplotlib.pyplot as pltfrom sklearn.linear_model import SGDClassifierfrom sklearn.datasets._samples_generator import make_blobsX, Y = make_blobs(n_samples=50, centers=2, random_state=0, cluster_std=0.60)clf = SGDClassifier(

原创 决策树--好瓜坏瓜

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") state

原创 识别手写体训练

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_...

原创 Euler算法

import numpy as npimport matplotlib.pyplot as pltx = 0y = 1a = np.ones(100)b = np.ones(100)t = 0for i in range(1,100): t = y * 1.1 - 0.2 * (x/y) x = x + 0.1 y = t a[i]=x b[i]=y plt.plot(a,b) plt.show()

原创 神经网络公式推导

原创 感知器zsbd

import numpy as npimport mathx = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])y = np.array([0, 1, 1, 1])alpha = 0.3a0 = np.random.random()a1 = np.random.random()a2 = np.random.random()a = np.array([a1, a2])eps = 1e-5e0 = 3e1 = 3e2 = 3i = 0fo.

原创 监督学习作业

import numpy as npimport matplotlib.pyplot as pltx = np.array([[2104,3],[1600,3],[2400,3],[1416,3]])t = np.array([402,336,369,232])alpha = 0.3a0 = np.random.random()a1 = np.random.random()a2 = np.random.random()a = np.array([a1,a2])eps = 1e-5e0

原创 numpy的部分基础应用

在numpy中有一个叫做广播机制的的运算，这非常有用。上图为索引示例广播机制类似一种矩阵的自动补全：import numpy as npx = np.array([1,2,3])y = np.array([1,2])print(x,y)[1 2 3] [1 2]简单的四则运算：import numpy as npx = np.array([10,20,30])y = np.array([1])a = x + yb = x - yc = x * .