Introduction. Example : Polynomial Curve Fitting ; Probability Theory ; Model Selection ; The Curse Of Dimensionality Decision Theory ; Information Theory -- Probability Distributions. Binary Vehicles ; Multinomial Variables ; The Gaussian Distribution ; The Exponential Family ; Nonparametric Methods -- Linear Models For Regression. Linear Basis Function Models ; The Bias-variance Decomposition ; Bayesian Linear Regression ; Bayesian Model Comparison ; The Evidence Approximation ; Limitations Of Fixed Basis Functions -- Linear Models For Classification. Discriminant Functions ; Probabilistic Generative Models ; Probabilistic Discrimitive Models ; The Laplace Approximation ; Bayesian Logistic Regression -- Neural Networks. Feed-forward Network Functions ; Network Training ; Error Backpropagation ; The Hessian Matrix ; Regularization In Neural Networks ; Mixture Density Networks ; Bayesian Neural Networks. Kernel Methods. Dual Representations ; Constructing Kernals ; Radial Basis Function Networks ; Gaussian Processes -- Sparse Kernel Machines. Maximum Margin Classifiers ; Relevance Vector Machines -- Graphical Models. Bayesian Networks ; Conditional Independence ; Markov Random Fields ; Inference In Graphical Models -- Mixture Models And Em. K-means Clustering ; Mixtures Of Gaussians ; An Alternative View Of Em ; The Em Algorithm In General -- Approximate Inference. Variational Inference ; Illustration : Variational Mixture Of Gaussians ; Variational Linear Regression ; Exponential Family Distributions ; Local Variational Methods ; Variational Logistic Regression ; Expectation Propagation -- Sampling Methods. Basic Sampling Algorithms ; Markov Chain Monte Carlo ; Gibbs Sampling ; Slice Sampling ; The Hybrid Monte Carlo Algorithm ; Estimating The Partition Function. Continuous Latent Variables. Principal Component Analysis ; Probabilistic Pca ; Kernel Pca ; Nonlinear Latent Variable Models -- Sequential Data. Markoc Models ; Hidden Markov Models ; Linear Dynamical Systems -- Combining Models. Bayesian Model Averaging ; Committees ; Boosting ; Tree-based Models ; Conditional Mixture Models -- Data Sets -- Probability Distributions -- Properties Of Matrices -- Calculus Of Variations -- Lagrange Multipliers. Christopher M. Bishop. Includes Bibliographical References (p. 711-728) And Index.

zlib/no-category/[美] Jake VanderPlas [VanderPlas, Jake]/Python数据科学手册_19085257.pdf

Pattern Recognition and Machine Learning (Information Science and Statistics)

Python数据科学手册 = Python data science handbook

(美)杰克·万托布拉斯(JakeVanderPlas)著

Jake VanderPlas; 陶俊杰 陈小莉

万托布拉斯 (VanderPlas, Jake)

Bishop, Christopher M.

Christopher M. Bishop

(美) 万托布拉斯

The People's Posts and Telecommunications Publishing House

Posts & Telecom Press

Palgrave Macmillan

Springer US

Copernicus

Information science and statistics, 8th print, New York, 2009

Information science and statistics, Cham, Switzerland, 2006

Tu ling cheng xu she ji cong shu, Di 1 ban, Beijing, 2018

Information science and statistics, New York, 2006

United States, United States of America

China, People's Republic, China

January 5, 2008

数据科学, 2018

PT, 2006

Bookmarks: p1 (p1): 第1章 IPython：超越Python
p1-1 (p1): 1.1 shell还是Notebook
p1-1-1 (p2): 1.1.1启动IPython shell
p1-1-2 (p2): 1.1.2启动Jupyter Notebook
p1-2 (p3): 1.2 IPython的帮助和文档
p1-2-1 (p3): 1.2.1用符号？获取文档
p1-2-2 (p4): 1.2.2通过符号？？获取源代码
p1-2-3 (p5): 1.2.3用Tab补全的方式探索模块
p1-3 (p7): 1.3 IPython shell中的快捷键
p1-3-1 (p7): 1.3.1导航快捷键
p1-3-2 (p7): 1.3.2文本输入快捷键
p1-3-3 (p8): 1.3.3命令历史快捷键
p1-3-4 (p9): 1.3.4其他快捷键
p1-4 (p9): 1.4 IPython魔法命令
p1-4-1 (p10): 1.4.1粘贴代码块：00185D60aste和1.4.2执行外部代码：%run
p1-4-2 (p11): 1.4.3计算代码运行时间：%timeit
p1-4-3 (p11): 1.4.4魔法函数的帮助：？、%magic和%lsmagic
p1-5 (p12): 1.5输入和输出历史
p1-5-1 (p12): 1.5.1 IPython的输入和输出对象
p1-5-2 (p13): 1.5.2下划线快捷键和以前的输出
p1-5-3 (p13): 1.5.3禁止输出
p1-5-4 (p13): 1.5.4相关的魔法命令
p1-6 (p14): 1.6 IPython和shell命令
p1-6-1 (p14): 1.6.1 shell快速入门
p1-6-2 (p15): 1.6.2 IPython中的shell命令
p1-6-3 (p15): 1.6.3在shell中传入或传出值
p1-7 (p16): 1.7与shell相关的魔法命令
p1-8 (p17): 1.8错误和调试
p1-8-1 (p17): 1.8.1控制异常：185d60mode
p1-8-2 (p19): 1.8.2调试：当阅读轨迹追溯不足以解决问题时
p1-9 (p21): 1.9代码的分析和计时
p1-9-1 (p22): 1.9.1代码段计时：%timeit和%time
p1-9-2 (p23): 1.9.2分析整个脚本：00185D60run
p1-9-3 (p24): 1.9.3用00185D60run进行逐行分析
p1-9-4 (p25): 1.9.4用%memit和%mprun进行内存分析
p1-10 (p26): 1.10 IPython参考资料
p1-10-1 (p26): 1.10.1网络资源
p1-10-2 (p27): 1.10.2相关图书
p2 (p28): 第2章 NumPy入门
p2-1 (p29): 2.1理解Python中的数据类型
p2-1-1 (p30): 2.1.1 Python整型不仅仅是一个整型
p2-1-2 (p31): 2.1.2 Python列表不仅仅是一个列表
p2-1-3 (p32): 2.1.3 Python中的固定类型数组
p2-1-4 (p32): 2.1.4从Python列表创建数组
p2-1-5 (p33): 2.1.5从头创建数组
p2-1-6 (p34): 2.1.6 NumPy标准数据类型
p2-2 (p35): 2.2 NumPy数组基础
p2-2-1 (p36): 2.2.1 NumPy数组的属性
p2-2-2 (p37): 2.2.2数组索引：获取单个元素
p2-2-3 (p38): 2.2.3数组切片：获取子数组
p2-2-4 (p41): 2.2.4数组的变形
p2-2-5 (p42): 2.2.5数组拼接和分裂
p2-3 (p44): 2.3 NumPy数组的计算：通用函数
p2-3-1 (p44): 2.3.1缓慢的循环
p2-3-2 (p45): 2.3.2通用函数介绍
p2-3-3 (p46): 2.3.3探索NumPy的通用函数
p2-3-4 (p49): 2.3.4高级的通用函数特性
p2-3-5 (p51): 2.3.5通用函数：更多的信息
p2-4 (p51): 2.4聚合：最小值、最大值和其他值
p2-4-1 (p51): 2.4.1数组值求和
p2-4-2 (p52): 2.4.2最小值和最大值
p2-4-3 (p54): 2.4.3示例：美国总统的身高是多少
p2-5 (p55): 2.5数组的计算：广播
p2-5-1 (p55): 2.5.1广播的介绍
p2-5-2 (p57): 2.5.2广播的规则
p2-5-3 (p60): 2.5.3广播的实际应用
p2-6 (p61): 2.6比较、掩码和布尔逻辑
p2-6-1 (p61): 2.6.1示例：统计下雨天数
p2-6-2 (p62): 2.6.2和通用函数类似的比较操作
p2-6-3 (p64): 2.6.3操作布尔数组
p2-6-4 (p66): 2.6.4将布尔数组作为掩码
p2-7 (p69): 2.7花哨的索引
p2-7-1 (p69): 2.7.1探索花哨的索引
p2-7-2 (p70): 2.7.2组合索引
p2-7-3 (p71): 2.7.3示例：选择随机点
p2-7-4 (p72): 2.7.4用花哨的索引修改值
p2-7-5 (p73): 2.7.5示例：数据区间划分
p2-8 (p75): 2.8数组的排序
p2-8-1 (p76): 2.8.1 NumPy中的快速排序：np.sort和np.argsort
p2-8-2 (p77): 2.8.2部分排序：分隔
p2-8-3 (p78): 2.8.3示例：K个最近邻
p2-9 (p81): 2.9结构化数据：NumPy的结构化数组
p2-9-1 (p83): 2.9.1生成结构化数组
p2-9-2 (p84): 2.9.2更高级的复合类型
p2-9-3 (p84): 2.9.3记录数组：结构化数组的扭转
p2-9-4 (p85): 2.9.4关于Pandas
p3 (p86): 第3章 Pandas数据处理
p3-1 (p86): 3.1安装并使用Pandas
p3-2 (p87): 3.2 Pandas对象简介
p3-2-1 (p87): 3.2.1 Pandas的Series对象
p3-2-2 (p90): 3.2.2 Pandas的Dat aFrame对象
p3-2-3 (p93): 3.2.3 Pandas的Index对象
p3-3 (p95): 3.3数据取值与选择
p3-3-1 (p95): 3.3.1 Series数据选择方法
p3-3-2 (p98): 3.3.2 DataFrame数据选择方法
p3-4 (p102): 3.4 Pandas数值运算方法
p3-4-1 (p102): 3.4.1通用函数：保留索引
p3-4-2 (p103): 3.4.2通用函数：索引对齐
p3-4-3 (p105): 3.4.3通用函数：DataFrame与Series的运算
p3-5 (p106): 3.5处理缺失值
p3-5-1 (p106): 3.5.1选择处理缺失值的方法
p3-5-2 (p107): 3.5.2 Pandas的缺失值
p3-5-3 (p110): 3.5.3处理缺失值
p3-6 (p113): 3.6层级索引
p3-6-1 (p113): 3.6.1多级索引Series
p3-6-2 (p116): 3.6.2多级索引的创建方法
p3-6-3 (p119): 3.6.3多级索引的取值与切片
p3-6-4 (p121): 3.6.4多级索引行列转换
p3-6-5 (p124): 3.6.5多级索引的数据累计方法
p3-7 (p125): 3.7合并数据集：Concat与Append操作
p3-7-1 (p126): 3.7.1知识回顾：NumPy数组的合并
p3-7-2 (p126): 3.7.2通过pd.concat实现简易合并
p3-8 (p129): 3.8 合并数据集：合并与连接
p3-8-1 (p129): 3.8.1关系代数
p3-8-2 (p130): 3.8.2数据连接的类型
p3-8-3 (p132): 3.8.3设置数据合并的键
p3-8-4 (p134): 3.8.4设置数据连接的集合操作规则
p3-8-5 (p135): 3.8.5重复列名：suffixes参数
p3-8-6 (p136): 3.8.6案例：美国各州的统计数据
p3-9 (p140): 3.9累计与分组
p3-9-1 (p140): 3.9.1行星数据
p3-9-2 (p141): 3.9.2 Pandas的简单累计功能
p3-9-3 (p142): 3.9.3 GroupBy：分割、应用和组合
p3-10 (p150): 3.10数据透视表
p3-10-1 (p150): 3.10.1演示数据透视表
p3-10-2 (p151): 3.10.2手工制作数据透视表
p3-10-3 (p151): 3.10.3数据透视表语法
p3-10-4 (p153): 3.10.4案例：美国人的生日
p3-11 (p157): 3.11向量化字符串操作
p3-11-1 (p157): 3.11.1 Pandas字符串操作简介
p3-11-2 (p159): 3.11.2 Pandas字符串方法列表
p3-11-3 (p163): 3.11.3案例：食谱数据库
p3-12 (p166): 3.12处理时间序列
p3-12-1 (p166): 3.12.1 Python的日期与时间工具
p3-12-2 (p169): 3.12.2 Pandas时间序列：用时间作索引
p3-12-3 (p170): 3.12.3 Pandas时间序列数据结构
p3-12-4 (p172): 3.12.4时间频率与偏移量
p3-12-5 (p173): 3.12.5重新取样、迁移和窗口
p3-12-6 (p178): 3.12.6更多学习资料
p3-12-7 (p179): 3.12.7案例：美国西雅图自行车统计数据的可视化
p3-13 (p184): 3.13高性能Pandas： eval（）与query（）
p3-13-1 (p184): 3.13.1 query（）与eval（）的设计动机：复合代数式
p3-13-2 (p185): 3.13.2用pandas.eval（）实现高性能运算
p3-13-3 (p187): 3.13.3用DataFrame.eval（）实现列间运算
p3-13-4 (p188): 3.13.4 DataFrame.query（）方法
p3-13-5 (p189): 3.13.5性能决定使用时机
p3-14 (p189): 3.14参考资料
p4 (p191): 第4章 Matplotlib数据可视化
p4-1 (p192): 4.1 Matplotlib常用技巧
p4-1-1 (p192): 4.1.1导入Matplotlib
p4-1-2 (p192): 4.1.2设置绘图样式
p4-1-3 (p192): 4.1.3用不用show（）？如何显示图形
p4-1-4 (p194): 4.1.4将图形保存为文件
p4-2 (p195): 4.2两种画图接口
p4-2-1 (p195): 4.2.1 MATLAB风格接口
p4-2-2 (p196): 4.2.2面向对象接口
p4-3 (p197): 4.3简易线形图
p4-3-1 (p199): 4.3.1调整图形：线条的颜色与风格
p4-3-2 (p200): 4.3.2调整图形：坐标轴上下限
p4-3-3 (p203): 4.3.3设置图形标签
p4-4 (p204): 4.4简易散点图
p4-4-1 (p205): 4.4.1用plt.plot画散点图
p4-4-2 (p206): 4.4.2用plt.scatter画散点图
p4-4-3 (p208): 4.4.3 plot与scatter：效率对比
p4-5 (p208): 4.5可视化异常处理
p4-5-1 (p209): 4.5.1基本误差线
p4-5-2 (p210): 4.5.2连续误差
p4-6 (p211): 4.6密度图与等高线图
p4-7 (p215): 4.7频次直方图、数据区间划分和分布密度
p4-8 (p219): 4.8配置图例
p4-8-1 (p221): 4.8.1选择图例显示的元素
p4-8-2 (p222): 4.8.2在图例中显示不同尺寸的点
p4-8-3 (p223): 4.8.3同时显示多个图例
p4-9 (p224): 4.9配置颜色条
p4-9-1 (p224): 4.9.1配置颜色条
p4-9-2 (p228): 4.9.2案例：手写数字
p4-10 (p230): 4.10多子图
p4-10-1 (p230): 4.10.1 plt.axes：手动创建子图
p4-10-2 (p231): 4.10.2 plt.subplot：简易网格子图
p4-10-3 (p233): 4.10.3 plt.subplots：用一行代码创建网格
p4-10-4 (p234): 4.10.4 plt.GridSpec：实现更复杂的排列方式
p4-11 (p235): 4.11文字与注释
p4-11-1 (p236): 4.11.1案例：节假日对美国出生率的影响
p4-11-2 (p237): 4.11.2坐标变换与文字位置
p4-11-3 (p239): 4.11.3箭头与注释
p4-12 (p241): 4.12自定义坐标轴刻度
p4-12-1 (p242): 4.12.1主要刻度与次要刻度
p4-12-2 (p243): 4.12.2隐藏刻度与标签
p4-12-3 (p244): 4.12.3增减刻度数量
p4-12-4 (p245): 4.12.4花哨的刻度格式
p4-12-5 (p247): 4.12.5格式生成器与定位器小结
p4-13 (p248): 4.13 Matplotlib自定义：配置文件与样式表
p4-13-1 (p248): 4.13.1手动配置图形
p4-13-2 (p249): 4.13.2修改默认配置：rcParams
p4-13-3 (p251): 4.13.3样式表
p4-14 (p255): 4.14用Matplotlib画三维图
p4-14-1 (p256): 4.14.1三维数据点与线
p4-14-2 (p256): 4.14.2三维等高线图
p4-14-3 (p258): 4.14.3线框图和曲面图
p4-14-4 (p259): 4.14.4曲面三角剖分
p4-15 (p261): 4.15用Basemap可视化地理数据
p4-15-1 (p263): 4.15.1地图投影
p4-15-2 (p267): 4.15.2画一个地图背景
p4-15-3 (p269): 4.15.3在地图上画数据
p4-15-4 (p270): 4.15.4案例：美国加州城市数据
p4-15-5 (p271): 4.15.5案例：地表温度数据
p4-16 (p273): 4.16用Seaborn做数据可视化
p4-16-1 (p274): 4.16.1 Seaborn与Matplotlib
p4-16-2 (p275): 4.16.2 Seaborn图形介绍
p4-16-3 (p283): 4.16.3案例：探索马拉松比赛成绩数据
p4-17 (p290): 4.17参考资料
p4-17-1 (p290): 4.17.1 Matplotlib资源
p4-17-2 (p290): 4.17.2其他Python画图程序库
p5 (p291): 第5章 机器学习
p5-1 (p291): 5.1什么是机器学习
p5-1-1 (p292): 5.1.1机器学习的分类
p5-1-2 (p292): 5.1.2机器学习应用的定性示例
p5-1-3 (p299): 5.1.3小结
p5-2 (p300): 5.2 Scikit-Learn简介
p5-2-1 (p300): 5.2.1 Scikit-Learn的数据表示
p5-2-2 (p302): 5.2.2 Scikit-Learn的评估器API
p5-2-3 (p309): 5.2.3应用：手写数字探索
p5-2-4 (p313): 5.2.4小结
p5-3 (p313): 5.3超参数与模型验证
p5-3-1 (p314): 5.3.1什么是模型验证
p5-3-2 (p317): 5.3.2选择最优模型
p5-3-3 (p322): 5.3.3学习曲线
p5-3-4 (p326): 5.3.4验证实践：网格搜索
p5-3-5 (p327): 5.3.5小结
p5-4 (p327): 5.4特征工程
p5-4-1 (p327): 5.4.1分类特征
p5-4-2 (p329): 5.4.2文本特征
p5-4-3 (p330): 5.4.3图像特征
p5-4-4 (p330): 5.4.4衍生特征
p5-4-5 (p332): 5.4.5缺失值填充
p5-4-6 (p332): 5.4.6特征管道
p5-5 (p333): 5.5专题：朴素贝叶斯分类
p5-5-1 (p333): 5.5.1贝叶斯分类
p5-5-2 (p334): 5.5.2高斯朴素贝叶斯
p5-5-3 (p336): 5.5.3多项式朴素贝叶斯
p5-5-4 (p339): 5.5.4朴素贝叶斯的应用场景
p5-6 (p340): 5.6专题：线性回归
p5-6-1 (p340): 5.6.1简单线性回归
p5-6-2 (p342): 5.6.2基函数回归
p5-6-3 (p346): 5.6.3正则化
p5-6-4 (p349): 5.6.4案例：预测自行车流量
p5-7 (p353): 5.7专题：支持向量机
p5-7-1 (p354): 5.7.1支持向量机的由来
p5-7-2 (p355): 5.7.2支持向量机：边界最大化
p5-7-3 (p363): 5.7.3案例：人脸识别
p5-7-4 (p366): 5.7.4支持向量机总结
p5-8 (p367): 5.8专题：决策树与随机森林
p5-8-1 (p367): 5.8.1随机森林的诱因：决策树
p5-8-2 (p371): 5.8.2评估器集成算法：随机森林
p5-8-3 (p373): 5.8.3随机森林回归
p5-8-4 (p374): 5.8.4案例：用随机森林识别手写数字
p5-8-5 (p376): 5.8.5随机森林总结
p5-9 (p376): 5.9专题：主成分分析
p5-9-1 (p377): 5.9.1主成分分析简介
p5-9-2 (p383): 5.9.2用PCA作噪音过滤
p5-9-3 (p385): 5.9.3案例：特征脸
p5-9-4 (p387): 5.9.4主成分分析总结
p5-10 (p388): 5.10专题：流形学习
p5-10-1 (p388): 5.10.1流形学习：“HELLO”
p5-10-2 (p389): 5.10.2多维标度法（MDS）
p5-10-3 (p391): 5.10.3将MDS用于流形学习
p5-10-4 (p393): 5.10.4非线性嵌入：当MDS失败时
p5-10-5 (p395): 5.10.5非线性流形：局部线性嵌入
p5-10-6 (p396): 5.10.6关于流形方法的一些思考
p5-10-7 (p397): 5.10.7示例：用Isomap处理人脸数据
p5-10-8 (p400): 5.10.8示例：手写数字的可视化结构
p5-11 (p402): 5.11专题：k-means聚类
p5-11-1 (p403): 5.11.1 k-means简介
p5-11-2 (p404): 5.11.2 k-means算法：期望最大化
p5-11-3 (p409): 5.11.3案例
p5-12 (p415): 5.12专题：高斯混合模型
p5-12-1 (p415): 5.12.1高斯混合模型（GMM）为什么会出现：k-means算法的缺陷
p5-12-2 (p417): 5.12.2一般化E-M：高斯混合模型
p5-12-3 (p421): 5.12.3将GMM用作密度估计
p5-12-4 (p425): 5.12.4示例：用GMM生成新的数据
p5-13 (p427): 5.13专题：核密度估计
p5-13-1 (p428): 5.13.1 KDE的由来：直方图
p5-13-2 (p431): 5.13.2核密度估计的实际应用
p5-13-3 (p433): 5.13.3示例：球形空间的KDE
p5-13-4 (p436): 5.13.4示例：不是很朴素的贝叶斯
p5-14 (p439): 5.14应用：人脸识别管道
p5-14-1 (p440): 5.14.1 HOG特征
p5-14-2 (p441): 5.14.2 HOG实战：简单人脸识别器
p5-14-3 (p445): 5.14.3注意事项与改进方案
p5-15 (p446): 5.15 机器学习参考资料
p5-15-1 (p446): 5.15.1 Python中的机器学习
p5-15-2 (p447): 5.15.2通用机器学习资源
p6 (p448): 关于作者
p7 (p448): 关于封面

The dramatic growth in practical applications for machine learning over the last ten years has been accompanied by many important developments in the underlying algorithms and techniques. For example, Bayesian methods have grown from a specialist niche to become mainstream, while graphical models have emerged as a general framework for describing and applying probabilistic techniques. The practical applicability of Bayesian methods has been greatly enhanced by the development of a range of approximate inference algorithms such as variational Bayes and expectation propagation, while new models based on kernels have had a significant impact on both algorithms and applications. This completely new textbook reflects these recent developments while providing a comprehensive introduction to the fields of pattern recognition and machine learning. It is aimed at advanced undergraduates or first-year PhD students, as well as researchers and practitioners. No previous knowledge of pattern recognition or machine learning concepts is assumed. Familiarity with multivariate calculus and basic linear algebra is required, and some experience in the use of probabilities would be helpful though not essential as the book includes a self-contained introduction to basic probability theory. The book is suitable for courses on machine learning, statistics, computer science, signal processing, computer vision, data mining, and bioinformatics. Extensive support is provided for course instructors, including more than 400 exercises, graded according to difficulty. Example solutions for a subset of the exercises are available from the book web site, while solutions for the remainder can be obtained by instructors from the publisher. The book is supported by a great deal of additional material, and the reader is encouraged to visit the book web site for the latest information. Christopher M. Bishop is Deputy Director of Microsoft Research Cambridge, and holds a Chair in Computer Science at the University of Edinburgh. He is a Fellow of Darwin College Cambridge, a Fellow of the Royal Academy of Engineering, and a Fellow of the Royal Society of Edinburgh. His previous textbook "Neural Networks for Pattern Recognition" has been widely adopted

Pattern recognition has its origins in engineering, whereas machine learning grew out of computer science. However, these activities can be viewed as two facets of the same field, and together they have undergone substantial development over the past ten years. In particular, Bayesian methods have grown from a specialist niche to become mainstream, while graphical models have emerged as a general framework for describing and applying probabilistic models. Also, the practical applicability of Bayesian methods has been greatly enhanced through the development of a range of approximate inference algorithms such as variational Bayes and expectation pro- gation. Similarly, new models based on kernels have had significant impact on both algorithms and applications. This new textbook reacts these recent developments while providing a comprehensive introduction to the fields of pattern recognition and machine learning. It is aimed at advanced undergraduates or first year PhD students, as wellas researchers and practitioners, and assumes no previous knowledge of pattern recognition or - chine learning concepts. Knowledge of multivariate calculus and basic linear algebra is required, and some familiarity with probabilities would be helpful though not essential as the book includes a self-contained introduction to basic probability theory.
Erscheinungsdatum: 17.08.2006

Pattern recognition has its origins in engineering, whereas machine learning grew out of computer science. However, these activities can be viewed as two facets of the same field, and together they have undergone substantial development over the past ten years. In particular, Bayesian methods have grown from a specialist niche to become mainstream, while graphical models have emerged as a general framework for describing and applying probabilistic models. Also, the practical applicability of Bayesian methods has been greatly enhanced through the development of a range of approximate inference algorithms such as variational Bayes and expectation propagation. Similarly, new models based on kernels have had a significant impact on both algorithms and applications. This new textbook reflects these recent developments while providing a comprehensive introduction to the fields of pattern recognition and machine learning. It is aimed at advanced undergraduates or first-year PhD students, as well as researchers and practitioners, and assumes no previous knowledge of pattern recognition or machine learning concepts. Knowledge of multivariate calculus and basic linear algebra is required, and some familiarity with probabilities would be helpful though not essential as the book includes a self-contained introduction to basic probability theory.

Ben shu gong wu zhang,Mei zhang jie shao yi dao liang ge Python shu ju ke xue zhong de zhong dian gong ju bao.Shou xian cong IPython he Jupyter kai shi,Ta men ti gong le shu ju ke xue jia xu yao de ji suan huan jing;Di 2 zhang jiang jie neng ti gong ndarray dui xiang de NumPy,Ta ke yi yong Python gao xiao di cun chu he cao zuo da xing shu zu;Di 3 zhang zhu yao she ji ti gong DataFrame dui xiang de Pandas,Ta ke yi yong Python gao xiao di cun chu he cao zuo dai biao qian de/ lie shi shu ju;Di 4 zhang de zhu jiao shi Matplotlib,Ta wei Python ti gong le xu duo shu ju ke shi hua gong neng;Di 5 zhang yi Scikit-Learn wei zhu,Zhei ge cheng xu ku wei zhong yao de ji qi xue xi suan fa ti gong le gao xiao zheng jie de Python ban shi xian

The field of pattern recognition has undergone substantial development over the years. This book reflects these developments while providing a grounding in the basic concepts of pattern recognition and machine learning. It is aimed at advanced undergraduates or first year PhD students, as well as researchers and practitioners

本书共五章,每章介绍一到两个Python数据科学中的重点工具包。首先从IPython和Jupyter开始,它们提供了数据科学家需要的计算环境;第2章讲解能提供ndarray对象的NumPy,它可以用Python高效地存储和操作大型数组;第3章主要涉及提供DataFrame对象的Pandas,它可以用Python高效地存储和操作带标签的/列式数据;第4章的主角是Matplotlib,它为Python提供了许多数据可视化功能;第5章以Scikit-Learn为主,这个程序库为重要的机器学习算法提供了高效整洁的Python版实现

2022-01-29