实例介绍
【实例截图】
【核心代码】
Contents Preface page ix PART I FOUNDATIONS OF TRANSFER LEARNING 1 1 Introduction 3 1.1 AI, Machine Learning and Transfer Learning 3 1.2 Transfer Learning: A Definition 7 1.3 Relationship to Existing Machine Learning Paradigms 11 1.4 Fundamental Research Issues in Transfer Learning 13 1.5 Applications of Transfer Learning 14 1.6 Historical Notes 17 1.7 About This Book 18 2 Instance-Based Transfer Learning 23 2.1 Introduction 23 2.2 Instance-Based Noninductive Transfer Learning 25 2.3 Instance-Based Inductive Transfer Learning 28 3 Feature-Based Transfer Learning 34 3.1 Introduction 34 3.2 Minimizing the Domain Discrepancy 35 3.3 Learning Universal Features 41 3.4 Feature Augmentation 43 4 Model-Based Transfer Learning 45 4.1 Introduction 45 4.2 Transfer through Shared Model Components 47 4.3 Transfer through Regularization 50 5 Relation-Based Transfer Learning 58 5.1 Introduction 58 5.2 Markov Logic Networks 61 5.3 Relation-Based Transfer Learning Based on MLNs 61 vi Contents 6 Heterogeneous Transfer Learning 68 6.1 Introduction 68 6.2 The Heterogeneous Transfer Learning Problem 70 6.3 Methodologies 71 6.4 Applications 90 7 Adversarial Transfer Learning 93 7.1 Introduction 93 7.2 Generative Adversarial Networks 94 7.3 Transfer Learning with Adversarial Models 97 7.4 Discussion 104 8 Transfer Learning in Reinforcement Learning 105 8.1 Introduction 105 8.2 Background 107 8.3 Inter-task Transfer Learning 113 8.4 Inter-domain Transfer Learning 122 9 Multi-task Learning 126 9.1 Introduction 126 9.2 The Definition 128 9.3 Multi-task Supervised Learning 128 9.4 Multi-task Unsupervised Learning 137 9.5 Multi-task Semi-supervised Learning 138 9.6 Multi-task Active Learning 138 9.7 Multi-task Reinforcement Learning 139 9.8 Multi-task Online Learning 139 9.9 Multi-task Multi-view Learning 140 9.10 Parallel and Distributed Multi-task Learning 140 10 Transfer Learning Theory 141 10.1 Introduction 141 10.2 Generalization Bounds for Multi-task Learning 142 10.3 Generalization Bounds for Supervised Transfer Learning 145 10.4 Generalization Bounds for Unsupervised Transfer Learning 148 11 Transitive Transfer Learning 151 11.1 Introduction 151 11.2 TTL over Mixed Graphs 153 11.3 TTL with Hidden Feature Representations 158 11.4 TTL with Deep Neural Networks 162 12 AutoTL: Learning to Transfer Automatically 168 12.1 Introduction 168 12.2 The L2T Framework 169 12.3 Parameterizing What to Transfer 170 12.4 Learning from Experiences 171 Contents vii 12.5 Inferring What to Transfer 174 12.6 Connections to Other Learning Paradigms 174 13 Few-Shot Learning 177 13.1 Introduction 177 13.2 Zero-Shot Learning 178 13.3 One-Shot Learning 184 13.4 Bayesian Program Learning 187 13.5 Poor Resource Learning 190 13.6 Domain Generalization 193 14 Lifelong Machine Learning 196 14.1 Introduction 196 14.2 Lifelong Machine Learning: A Definition 197 14.3 Lifelong Machine Learning through Invariant Knowledge 198 14.4 Lifelong Machine Learning in Sentiment Classification 199 14.5 Shared Model Components as Multi-task Learning 203 14.6 Never-Ending Language Learning 204 PART II APPLICATIONS OF TRANSFER LEARNING 209 15 Privacy-Preserving Transfer Learning 211 15.1 Introduction 211 15.2 Differential Privacy 212 15.3 Privacy-Preserving Transfer Learning 215 16 Transfer Learning in Computer Vision 221 16.1 Introduction 221 16.2 Overview 222 16.3 Transfer Learning for Medical Image Analysis 229 17 Transfer Learning in Natural Language Processing 234 17.1 Introduction 234 17.2 Transfer Learning in NLP 234 17.3 Transfer Learning in Sentiment Analysis 241 18 Transfer Learning in Dialogue Systems 257 18.1 Introduction 257 18.2 Problem Formulation 259 18.3 Transfer Learning in Spoken Language Understanding 259 18.4 Transfer Learning in Dialogue State Tracker 262 18.5 Transfer Learning in DPL 263 18.6 Transfer Learning in Natural Language Generation 268 18.7 Transfer Learning in End-to-End Dialogue Systems 269 viii Contents 19 Transfer Learning in Recommender Systems 279 19.1 Introduction 279 19.2 What to Transfer in Recommendation 280 19.3 News Recommendation 284 19.4 VIP Recommendation in Social Networks 288 20 Transfer Learning in Bioinformatics 293 20.1 Introduction 293 20.2 Machine Learning Problems in Bioinformatics 294 20.3 Biological Sequence Analysis 295 20.4 Gene Expression Analysis and Genetic Analysis 299 20.5 Systems Biology 299 20.6 Biomedical Text and Image Mining 301 20.7 Deep Learning for Bioinformatics 302 21 Transfer Learning in Activity Recognition 307 21.1 Introduction 307 21.2 Transfer Learning for Wireless Localization 307 21.3 Transfer Learning for Activity Recognition 316 22 Transfer Learning in Urban Computing 324 22.1 Introduction 324 22.2 “What to Transfer” in Urban Computing 325 22.3 Key Issues of Transfer Learning in Urban Computing 326 22.4 Chain Store Recommendation 327 22.5 Air-Quality Prediction 330 23 Concluding Remarks 334 References 336 Index 377
标签:
小贴士
感谢您为本站写下的评论,您的评论对其它用户来说具有重要的参考价值,所以请认真填写。
- 类似“顶”、“沙发”之类没有营养的文字,对勤劳贡献的楼主来说是令人沮丧的反馈信息。
- 相信您也不想看到一排文字/表情墙,所以请不要反馈意义不大的重复字符,也请尽量不要纯表情的回复。
- 提问之前请再仔细看一遍楼主的说明,或许是您遗漏了。
- 请勿到处挖坑绊人、招贴广告。既占空间让人厌烦,又没人会搭理,于人于己都无利。
关于好例子网
本站旨在为广大IT学习爱好者提供一个非营利性互相学习交流分享平台。本站所有资源都可以被免费获取学习研究。本站资源来自网友分享,对搜索内容的合法性不具有预见性、识别性、控制性,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,平台无法对用户传输的作品、信息、内容的权属或合法性、安全性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论平台是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二与二十三条之规定,若资源存在侵权或相关问题请联系本站客服人员,点此联系我们。关于更多版权及免责申明参见 版权及免责申明
网友评论
我要评论