Advertisement

Evolutionary Learning: Advances in Theories and Algorithms

  • Zhi-Hua Zhou
  • Yang Yu
  • Chao Qian
Book

Table of contents

  1. Front Matter
    Pages I-XII
  2. Introduction

    1. Front Matter
      Pages 1-1
    2. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 3-10
    3. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 11-26
  3. Analysis Methodology

    1. Front Matter
      Pages 27-27
    2. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 29-39
    3. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 41-50
    4. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 51-67
    5. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 69-80
  4. Theoretical Perspectives

    1. Front Matter
      Pages 81-81
    2. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 83-92
    3. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 93-108
    4. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 109-128
    5. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 129-153
    6. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 155-173
    7. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 175-194
  5. Learning Algorithms

    1. Front Matter
      Pages 195-195
    2. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 197-214
    3. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 215-231
    4. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 233-254
    5. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 255-268
    6. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 269-283
    7. Zhi-Hua Zhou, Yang Yu, Chao Qian
      Pages 285-293
  6. Back Matter
    Pages 295-361

About this book

Introduction

Many machine learning tasks involve solving complex optimization problems, such as working on non-differentiable, non-continuous, and non-unique objective functions; in some cases it can prove difficult to even define an explicit objective function. Evolutionary learning applies evolutionary algorithms to address optimization problems in machine learning, and has yielded encouraging outcomes in many applications. However, due to the heuristic nature of evolutionary optimization, most outcomes to date have been empirical and lack theoretical support. This shortcoming has kept evolutionary learning from being well received in the machine learning community, which favors solid theoretical approaches.   

Recently there have been considerable efforts to address this issue. This book presents a range of those efforts, divided into four parts. Part I briefly introduces readers to evolutionary learning and provides some preliminaries, while Part II presents general theoretical tools for the analysis of running time and approximation performance in evolutionary algorithms. Based on these general tools, Part III presents a number of theoretical findings on major factors in evolutionary optimization, such as recombination, representation, inaccurate fitness evaluation, and population. In closing, Part IV addresses the development of evolutionary learning algorithms with provable theoretical guarantees for several representative tasks, in which evolutionary learning offers excellent performance.

Keywords

Artificial intelligence Machine Learning Evolutionary Learning Evolutionary Algorithms Evolutionary Optimization Evolutionary Computation Theoretical Foundation of Evolutionary Learning Selective Ensemble Subset Selection Multi-Objective Optimization

Authors and affiliations

  • Zhi-Hua Zhou
    • 1
  • Yang Yu
    • 2
  • Chao Qian
    • 3
  1. 1.Nanjing UniversityNanjingChina
  2. 2.Nanjing UniversityNanjingChina
  3. 3.Nanjing UniversityNanjingChina

Bibliographic information

  • DOI https://doi.org/10.1007/978-981-13-5956-9
  • Copyright Information Springer Nature Singapore Pte Ltd. 2019
  • Publisher Name Springer, Singapore
  • eBook Packages Computer Science
  • Print ISBN 978-981-13-5955-2
  • Online ISBN 978-981-13-5956-9
  • Buy this book on publisher's site