没有合适的资源?快使用搜索试试~ 我知道了~
首页机器学习入门:应用与方法详解
机器学习入门:应用与方法详解
需积分: 9 9 下载量 161 浏览量
更新于2024-07-19
收藏 46.37MB PDF 举报
《机器学习入门》第三版是一本全面介绍机器学习领域的教材,旨在教导读者如何编程计算机利用实例数据或过去经验解决特定问题。该书不仅关注于基础概念,还涵盖了广泛的主题,使读者能够深入了解不同领域的理论基础,如统计学、模式识别、神经网络、人工智能、信号处理、控制和数据挖掘等。作者通过将各种方法整合,提供了一种统一的方法来理解和处理机器学习问题。 书中首先定义了机器学习并列举了实际应用的例子,如预测消费者行为、面部识别、语音识别、机器人优化和生物信息学数据分析。对于学习者来说,本书特别强调了监督学习、贝叶斯决策理论、参数化方法、多元方法、维度降低、聚类分析、非参数方法、决策树、线性判别、多层感知器、局部模型、隐马尔可夫模型、评估和比较分类算法、结合多个学习器以及强化学习等核心概念和技术。所有算法都以易于理解的方式进行解释,使得学生可以直接将书中的理论知识转化为计算机程序。 该书适合高级本科生和研究生阅读,前提是他们已经具备计算机编程、概率论、微积分和线性代数的基础知识。对于计算机科学领域的工程师而言,本书同样具有价值,因为它提供了机器学习方法的实际应用指导。此外,该系列图书的完整列表可在本书末尾找到。 版权方面,未经麻省理工学院出版社书面许可,不得以任何形式(包括复印、录音或信息存储与检索)复制本书的任何部分。关于批量折扣的更多信息,可通过电子邮件special_sales@mitpress.mit.edu查询。本书采用10/13磅的Lucida Bright字体排版,并由作者使用LaTeX2ε编纂,印刷和装订在美国。图书馆编目信息包含在书中。
资源详情
资源推荐
xiv Contents
16.3.2 Univariate Case: Unknown Mean, Unknown
Variance 453
16.3.3 Multivariate Case: Unknown Mean, Unknown
Covariance 455
16.4 Bayesian Estimation of the Parameters of a Function 456
16.4.1 Regression 456
16.4.2 Regression with Prior on Noise Precision 460
16.4.3 The Use of Basis/Kernel Functions 461
16.4.4 Bayesian Classification 463
16.5 Choosing a Prior 466
16.6 Bayesian Model Comparison 467
16.7 Bayesian Estimation of a Mixture Model 470
16.8 Nonparametric Bayesian Modeling 473
16.9 Gaussian Processes 474
16.10 Dirichlet Processes and Chinese Restaurants 478
16.11 Latent Dirichlet Allocation 480
16.12 Beta Processes and Indian Buffets 482
16.13 Notes 483
16.14 Exercises 484
16.15 References 485
17 Combining Multiple Learners 487
17.1 Rationale 487
17.2 Generating Diverse Learners 488
17.3 Model Combination Schemes 491
17.4 Voting 492
17.5 Error-Correcting Output Codes 496
17.6 Bagging 498
17.7 Boosting 499
17.8 The Mixture of Experts Revisited 502
17.9 Stacked Generalization 504
17.10 Fine-Tuning an Ensemble 505
17.10.1 Choosing a Subset of the Ensemble 506
17.10.2 Constructing Metalearners 506
17.11 Cascading 507
17.12 Notes 509
17.13 Exercises 511
17.14 References 513
Preface xix
who send me words of appreciation, criticism, or errata, or who provide
feedback in any other way. Please keep them coming. My email address
is alpaydin@boun.edu.tr. The book’s web site is
http://www.cmpe.boun.edu.tr/∼ethem/i2ml3e.
It has been a pleasure to work with the MIT Press again on this third edi-
tion, and I thank Marie Lufkin Lee, Marc Lowenthal, and Kathleen Caruso
for all their help and support.
Contents xv
18 Reinforcement Learning 517
18.1 Introduction 517
18.2 Single State Case: K-Armed Bandit 519
18.3 Elements of Reinforcement Learning 520
18.4 Model-Based Learning 523
18.4.1 Value Iteration 523
18.4.2 Policy Iteration 524
18.5 Temporal Difference Learning 525
18.5.1 Exploration Strategies 525
18.5.2 Deterministic Rewards and Actions 526
18.5.3 Nondeterministic Rewards and Actions 527
18.5.4 Eligibility Traces 530
18.6 Generalization 531
18.7 Partially Observable States 534
18.7.1 The Setting 534
18.7.2 Example: The Tiger Problem 536
18.8 Notes 541
18.9 Exercises 542
18.10 References 544
19 Design and Analysis of Machine Learning Experiments 547
19.1 Introduction 547
19.2 Factors, Response, and Strategy of Experimentation 550
19.3 Response Surface Design 553
19.4 Randomization, Replication, and Blocking 554
19.5 Guidelines for Machine Learning Experiments 555
19.6 Cross-Validation and Resampling Methods 558
19.6.1 K-Fold Cross-Validation 559
19.6.2 5 × 2Cross-Validation 560
19.6.3 Bootstrapping 561
19.7 Measuring Classifier Performance 561
19.8 Interval Estimation 564
19.9 Hypothesis Testing 568
19.10 Assessing a Classification Algorithm’s Performance 570
19.10.1 Binomial Test 571
19.10.2 Approximate Normal Test 572
19.10.3 t Test 572
19.11 Comparing Two Classification Algorithms 573
19.11.1 McNemar’s Test 573
xvi Contents
19.11.2 K-Fold Cross-Validated Paired t Test 573
19.11.3 5 × 2cvPairedt Test 574
19.11.4 5 × 2cvPairedF Test 575
19.12 Comparing Multiple Algorithms: Analysis of Variance 576
19.13 Comparison over Multiple Datasets 580
19.13.1 Comparing Two Algorithms 581
19.13.2 Multiple Algorithms 583
19.14 Multivariate Tests 584
19.14.1 Comparing Two Algorithms 585
19.14.2 Comparing Multiple Algorithms 586
19.15 Notes 587
19.16 Exercises 588
19.17 References 590
A Probability 593
A.1 Elements of Probability 593
A.1.1 Axioms of Probability 594
A.1.2 Conditional Probability 594
A.2 Random Variables 595
A.2.1 Probability Distribution and Density Functions 595
A.2.2 Joint Distribution and Density Functions 596
A.2.3 Conditional Distributions 596
A.2.4 Bayes’ Rule 597
A.2.5 Expectation 597
A.2.6 Variance 598
A.2.7 Weak Law of Large Numbers 599
A.3 Special Random Variables 599
A.3.1 Bernoulli Distribution 599
A.3.2 Binomial Distribution 600
A.3.3 Multinomial Distribution 600
A.3.4 Uniform Distribution 600
A.3.5 Normal (Gaussian) Distribution 601
A.3.6 Chi-Square Distribution 602
A.3.7 t Distribution 603
A.3.8 F Distribution 603
A.4 References 603
Index 605
Preface
Machine learning must be one of the fastest growing fields in computer
science. It is not only that the data is continuously getting “bigger,” but
also the theory to process it and turn it into knowledge. In various fields
of science, from astronomy to biology, but also in everyday life, as dig-
ital technology increasingly infiltrates our daily existence, as our digital
footprint deepens, more data is continuously generated and collected.
Whether scientific or personal, data that just lies dormant passively is
not of any use, and smart people have been finding ever new ways to
make use of that data and turn it into a useful product or service. In this
transformation, machine learning plays a larger and larger role.
This data evolution has been continuing even stronger since the sec-
ond edition appeared in 2010. Every year, datasets are getting larger. Not
only has the number of observations grown, but the number of observed
attributes has also increased significantly. There is more structure to
the data: It is not just numbers and character strings any more but im-
ages, video, audio, documents, web pages, click logs, graphs, and so on.
More and more, the data moves away from the parametric assumptions
we used to make—for example, normality. Frequently, the data is dy-
namic and so there is a time dimension. Sometimes, our observations
are multi-view—for the same object or event, we have multiple sources
of information from different sensors and modalities.
Our belief is that b ehind all this seemingly complex and voluminous
data, there lies a simple explanation. That although the data is big, it can
be explained in terms of a relatively simple model with a small number of
hidden factors and their interaction. Think about millions of customers
who each day buy thousands of products online or from their local super-
market. This implies a very large database of transactions, but there is a
剩余639页未读,继续阅读
lilipolly
- 粉丝: 2
- 资源: 4
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 计算机人脸表情动画技术发展综述
- 关系数据库的关键字搜索技术综述:模型、架构与未来趋势
- 迭代自适应逆滤波在语音情感识别中的应用
- 概念知识树在旅游领域智能分析中的应用
- 构建is-a层次与OWL本体集成:理论与算法
- 基于语义元的相似度计算方法研究:改进与有效性验证
- 网格梯度多密度聚类算法:去噪与高效聚类
- 网格服务工作流动态调度算法PGSWA研究
- 突发事件连锁反应网络模型与应急预警分析
- BA网络上的病毒营销与网站推广仿真研究
- 离散HSMM故障预测模型:有效提升系统状态预测
- 煤矿安全评价:信息融合与可拓理论的应用
- 多维度Petri网工作流模型MD_WFN:统一建模与应用研究
- 面向过程追踪的知识安全描述方法
- 基于收益的软件过程资源调度优化策略
- 多核环境下基于数据流Java的Web服务器优化实现提升性能
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功