idealism_的博客

原创 随机梯度下降法

import randomimport numpy as npt = np.array([400, 336, 369, 232, 540])X = np.array([[2104, 3], [1600, 3], [2400, 3], [1416, 2], [3000, 4]])theta = [1, 1]alpha = 0.0000001epsilon = 1e-5loss = 10error = 0max_iters = 10000iter_count = 0while (

原创 pyTorch-图卷积神经网络

import torchimport torch.nn.functional as Ffrom torch_geometric.nn import GCNConvfrom torch_geometric.nn import MessagePassingfrom torch_geometric.utils import add_self_loops, degreefrom torch_geometric.datasets import Planetoiddataset = Planetoid

原创 LDA公式推导

原创 西瓜书决策树数据2.0推导计算

原创 强化学习 python实现

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

原创 paddle paddle手写数字识别

import paddlefrom paddle.nn import Linearimport paddle.nn.functional as Fimport osimport numpy as npimport matplotlib.pyplot as pltfrom paddle.vision.datasets import MNISTtrain_dataset = paddle.vision.datasets.MNIST(mode='train')train_data0 = np.a

原创 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 plt# print(paddle.__version__)transform = ToTensor()cifar10_train = paddle.vision.datasets.Cifar10(mode='train'

原创 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 plt# print(paddle.__version__)transform = ToTensor()cifar10_train = paddle.vision.datasets.Cifar10(mode='train'

原创 旋度的散度恒为0公式推导

原创 主成分分析PCA算法-python实现

import numpy as npimport matplotlib.pyplot as pltX = np.array([2.5, 0.5, 2.2, 1.9, 3.1, 2.3, 2.0, 1.0, 1.5, 1.1])Y = np.array([2.4, 0.7, 2.9, 2.2, 3.0, 2.7, 1.6, 1.1, 1.6, 0.9])X1 = sum(X) / len(X)Y1 = sum(Y) / len(Y)for i in range(len(X)): X[i

原创 隐马尔可夫链-viterbi算法python实现

import numpy as npclimate = ["sunny", "rain"]behavior = ["walk", "shop", "clean"]start_p = [0.6, 0.4] # rain的概率为0.6,sunny的概率为0.4trans = [[0.7, 0.3], [0.4, 0.6]]# trans_p_rain = [0.7, 0.3] # rain sunny# tarns_p_sunny = [0.4, 0.6]emit = [[0.1, 0.4,

原创 改进的欧拉算法-python代码实现

import matplotlib.pyplot as plth = 0.1 # 步长yy = []xx = []yy.append(1)xx.append(0)def y1(m, n): return m - 2 * n / mfor i in range(100): k1 = y1(yy[i], xx[i]) y = yy[i] + h * y1(yy[i], xx[i]) xx.append(xx[i] + h) k2 = y1(y

原创 BP神经网络-python代码实现

神经网络模型import randomimport mathrate = 0.01x = [1, 1, 1]print("迭代前")weight1 = [random.random(), random.random(), random.random(), random.random()] # 表示输入层第一个元素与隐藏层每个元素之间的权值weight2 = [random.random(), random.random(), random.random(), random.random

原创 神经网络反向传播算法

神经网络反向传播算法公式推导

原创 20210915作业

原创 感知器算法

import randomimport mathimport numpy as nprate = 0.0001X = [[1, 1, 1], [1, 0, 0], [1, 1, 0], [1, 0, 1]]t = [1, 0, 0, 0]m = len(X)weights = [random.random(), random.random(), random.random()]delta = [5, 5, 5]epsilon = 1e-6#

转载 python中numpy的使用 学习过程

import numpy as npdata = np.array([1,2,3])print(data)[1 2 3]data.max()3np.ones(3)array([1., 1., 1.])np.zeros(3)array([0., 0., 0.])np.random.random(3)array([0.57604932, 0.97820094, 0.34434803])data1 = np.array([1,2])ones = np.ones(2)

原创 梯度下降算法学习记录

import numpy as npt = np.array([400,336,369,232,540])X = np.array([[1,2104,3],[1,1600,3],[1,2400,3],[1,1416,2],[1,3000,4]])theta0 = 1theta1 = 1theta2 = 1alpha = 0.000001epsilon = 1e-5e0 = 1e1 = 1e2 = 1m = len(X)for i in range(5): while