m0_47660709的博客

import randomimport mathfrom matplotlib import pyplot as plt# 生成数据DATA = [[random.randint(-100, -50) for _ in range(2)] for __ in range(100)]for _ in range(100): DATA.append([random.randint(50, 100) for _ in range(2)])random.shuffle(DATA)EPS =

import torchimport torch.nn.functional as Ffrom torch_geometric.nn import GCNConvfrom torch_geometric.datasets import Planetoiddataset = Planetoid(root='/tmp/Cora', name='Cora')class Net(torch.nn.Module): def __init__(self): super(Net, s

信息熵：Ent(D)=−∑k=1∣y∣pklog⁡2pkEnt(D) = -\sum ^{\lvert y \rvert}_{k=1} p_k \log_2 p_kEnt(D)=−∑k=1∣y∣​pk​log2​pk​信息增益：Gain(D,a)=Ent(D)−∑v=1V∣Dv∣∣D∣Ent(Dv)Gain(D, a) = Ent(D) - \sum_{v=1}^V \frac{\lvert D^v \rvert}{\lvert D \rvert} Ent(D^v)Gain(D,a)=Ent(D)−∑v=

import math# 属性的取值范围(0~n-1)data = [[0, 0, 0, 0], [0, 0, 0, 1], [0, 0, 1, 0], [1, 0, 1, 1], [0, 1, 0, 0], [0, 1, 0, 1], [1, 1, 1, 0], [0, 1, 1, 1], [0, 1, 0, 1]]label = [1, 1, 0, 1, 0, 1, 0

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

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

from paddle.batch import batchimport paddle.nn.functional as Fimport numpy as npimport matplotlib.pyplot as pltfrom paddle.nn import Linearfrom paddle.nn.functional.common import padfrom paddle.vision.transforms import ToTensortransform = ToTensor(

import numpy as npdata = np.array([[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]])x1 = sum(data[:, 0]) / 10.0y1 = sum(data[:, 1]) / 10.0DataAdjust = data - [x1,

∇×A=∣lx^y^z^∂∂x∂∂y∂∂zAxAyAz∣=x^⋅∂Az∂y+y^⋅∂Ax∂z+z^⋅∂Ay∂x−z^⋅∂Ax∂y−x^⋅∂Ay∂z−y^⋅∂Az∂x=x^(∂Az∂y−∂Ay∂z)+y^(∂Ax∂z−∂Az∂x)+z^(∂Ay∂x−∂Ax∂y)\nabla \times A = \begin{vmatrix}{l}\hat x & \hat y & \hat z \\ \frac{\partial}{\partial x} & \frac{\partial}{\par

weather = ['Rainy', 'Sunny']activity = ['walk', 'shop', 'clean']transition_probability = [[0.7, 0.3], [0.4, 0.6]]emission_probability = [[0.1, 0.4, 0.5], [0.6, 0.3, 0.1]]observations = [0, 1, 2]res = []last_probability = [0.6, 0.4]father = [[] fo.

import matplotlib.pyplot as pltx, y = 0.0, 1.0tarX = 10.0step = 0.1X, Y = [x], [y]def f(x:float, y:float): return y - 2 * x / ywhile x <= tarX: k1 = f(x, y) k2 = f(x + step, y + k1 * step) y = y + 0.5 * (k1 + k2) * step x =

import numpy as npdelta = 1.0class Neuron: def __init__(self, lastLayerNodeNumber: int) -> None: self.n = lastLayerNodeNumber self.w = [np.random.rand() for _ in range(lastLayerNodeNumber)] @staticmethod def sigmod(x: fl

规定yijy_{ij}yij​为第iii层网络第

欧拉公式以及凉鞋问题欧拉公式代码import matplotlib.pyplot as pltx, y = 0.0, 1.0step = 0.1def f(x:float, y:float): return y - 2 * x / yX, Y = [x], [y]while x < 10.0: k = f(x, y) y = y + k * step x = x + step X.append(x) Y.append(y)pr

感知器算法公式推导Li=(σ(Σj=02xjiωj)−ti)2L_{i}=(\sigma(\Sigma_{j=0}^{2}x^{i}_{j}\omega_{j})-t_{i})^{2}Li​=(σ(Σj=02​xji​ωj​)−ti​)2.∇i=dLdωi=2(σ(Σj=02xjiωj)−ti)σ(Σj=02xjiωj)(1−σ(Σj=02xjiωj))xij\nabla_{i}=\frac{dL}{d\omega_{i}}=2(\sigma(\Sigma_{j=0}^{2}x^{i}_{j}\ome

文章目录numpy array的一些基本操作numpy的广播机制聚合函数的使用矩阵相乘矩阵的索引与切片聚合矩阵的转置生成高维数组数组的拆分垂直拆分水平拆分dsplitnumpy基本加减和取行操作矩阵删除、插入、尾部添加操作delete函数参数列表示例insert函数参数列表示例append函数参数列表示例利用numpy的chioce生成数组参数列表示例argmax：获取数组中最大值的索引值参数列表示例linspace的用法参数列表示例numpy array的一些基本操作data = np.array([

import numpy as np'''52104 3 3001600 3 3302400 3 3691416 2 2323000 4 540'''X = [[1, 2104, 3], [1, 1600, 3], [1, 2400, 3], [1, 1416, 2], [1, 3000, 4]]T = [300, 330, 369, 232, 540]theta = [1.0, 1.0, 1.0]alpha = 0.000001e1

安装在conda官网下载安装conda.打开terminal输入conda -V，回车显示conda的版本说明安装成功。将conda更新到最新版本conda update conda可将conda更新到最新版本。查看已存在的虚拟环境conda env list可查看已存在的虚拟环境。这些虚拟环境都存储在Anaconda根目录下的env文件夹中。创建一个虚拟环境conda create -n env_name python=python_version，其中env_name是你想创建的