Dynamic Fuzzy Machine Learning

Book description

Machine learning is widely used for data analysis. Dynamic fuzzy data are one of the most difficult types of data to analyse in the field of big data, cloud computing, the Internet of Things, and quantum information. At present, the processing of this kind of data is not very mature. The authors carried out more than 20 years of research, and show in this book their most important results. The seven chapters of the book are devoted to key topics such as dynamic fuzzy machine learning models, dynamic fuzzy self-learning subspace algorithms, fuzzy decision tree learning, dynamic concepts based on dynamic fuzzy sets, semi-supervised multi-task learning based on dynamic fuzzy data, dynamic fuzzy hierarchy learning, examination of multi-agent learning model based on dynamic fuzzy logic. This book can be used as a reference book for senior college students and graduate students as well as college teachers and scientific and technical personnel involved in computer science, artificial intelligence, machine learning, automation, data analysis, mathematics, management, cognitive science, and finance. It can be also used as the basis for teaching the principles of dynamic fuzzy learning.

Table of contents

  1. Cover
  2. Title Page
  3. Copyright
  4. Contents
  5. Preface
  6. 1 Dynamic fuzzy machine learning model
    1. 1.1 Problem statement
    2. 1.2 DFML model
      1. 1.2.1 Basic concept of DFMLs
      2. 1.2.2 DFML algorithm
      3. 1.2.3 DFML geometric model description
      4. 1.2.4 Simulation examples
    3. 1.3 Relative algorithm of DFMLS
      1. 1.3.1 Parameter learning algorithm for DFMLS
      2. 1.3.2 Maximum likelihood estimation algorithm in DFMLS
    4. 1.4 Process control model of DFMLS
      1. 1.4.1 Process control model of DFMLS
      2. 1.4.2 Stability analysis
      3. 1.4.3 Design of dynamic fuzzy learning controller
      4. 1.4.4 Simulation examples
    5. 1.5 Dynamic fuzzy relational learning algorithm
      1. 1.5.1 An outline of relational learning
      2. 1.5.2 Problem introduction
      3. 1.5.3 DFRL algorithm
      4. 1.5.4 Algorithm analysis
    6. 1.6 Summary
    7. References
  7. 2 Dynamic fuzzy autonomic learning subspace algorithm
    1. 2.1 Research status of autonomic learning
    2. 2.2 Theoretical system of autonomous learning subspace based on DFL
      1. 2.2.1 Characteristics of AL
      2. 2.2.2 Axiom system of AL subspace
    3. 2.3 Algorithm of ALSS based on DFL
      1. 2.3.1 Preparation of algorithm
      2. 2.3.2 Algorithm of ALSS based on DFL
      3. 2.3.3 Case analysis
    4. 2.4 Summary
    5. References
  8. 3 Dynamic fuzzy decision tree learning
    1. 3.1 Research status of decision trees
      1. 3.1.1 Overseas research status
      2. 3.1.2 Domestic research status
    2. 3.2 Decision tree methods for a dynamic fuzzy lattice
      1. 3.2.1 ID3 algorithm and examples
      2. 3.2.2 Characteristics of dynamic fuzzy analysis of decision trees
      3. 3.2.3 Representation methods for dynamic fuzzy problems in decision trees
      4. 3.2.4 DFDT classification attribute selection algorithm
      5. 3.2.5 Dynamic fuzzy binary decision tree
    3. 3.3 DFDT special attribute processing technique
      1. 3.3.1 Classification of attributes
      2. 3.3.2 Process used for enumerated attributes by DFDT
      3. 3.3.3 Process used for numeric attributes by DFDT
      4. 3.3.4 Methods to process missing value attributes in DFDT
    4. 3.4 Pruning strategy of DFDT
      1. 3.4.1 Reasons for pruning
      2. 3.4.2 Methods of pruning
      3. 3.4.3 DFDT pruning strategy
    5. 3.5 Application
      1. 3.5.1 Comparison of algorithm execution
      2. 3.5.2 Comparison of training accuracy
      3. 3.5.3 Comprehensibility comparisons
    6. 3.6 Summary
    7. References
  9. 4 Concept learning based on dynamic fuzzy sets
    1. 4.1 Relationship between dynamic fuzzy sets and concept learning
    2. 4.2 Representation model of dynamic fuzzy concepts
    3. 4.3 DF concept learning space model
      1. 4.3.1 Order model of DF concept learning
      2. 4.3.2 DF concept learning calculation model
      3. 4.3.3 Dimensionality reduction model of DF instances
      4. 4.3.4 Dimensionality reduction model of DF attribute space
    4. 4.4 Concept learning model based on DF lattice
      1. 4.4.1 Construction of classical concept lattice
      2. 4.4.2 Constructing lattice algorithm based on DFS
      3. 4.4.3 DF Concept Lattice Reduction
      4. 4.4.4 Extraction of DF concept rules
      5. 4.4.5 Examples of algorithms and experimental analysis
    5. 4.5 Concept learning model based on DFDT
      1. 4.5.1 DF concept tree and generating strategy
      2. 4.5.2 Generation of DF Concepts
      3. 4.5.3 DF concept rule extraction and matching algorithm
    6. 4.6 Application examples and analysis
      1. 4.6.1 Face recognition experiment based on DF concept lattice
      2. 4.6.2 Data classification experiments on UCI datasets
    7. 4.7 Summary
    8. References
  10. 5 Semi-supervised multi-task learning based on dynamic fuzzy sets
    1. 5.1 Introduction
      1. 5.1.1 Review of semi-supervised multi-task learning
      2. 5.1.2 Problem statement
    2. 5.2 Semi-supervised multi-task learning model
      1. 5.2.1 Semi-supervised learning
      2. 5.2.2 Multi-task learning
    3. 5.3 Semi-supervised multi-task learning model based on DFS
      1. 5.3.1 Dynamic fuzzy machine learning model
      2. 5.3.2 Dynamic fuzzy semi-supervised learning model
      3. 5.3.3 DFSSMTL model
    4. 5.4 Dynamic fuzzy semi-supervised multi-task matching algorithm
      1. 5.4.1 Dynamic fuzzy random probability
      2. 5.4.2 Dynamic fuzzy semi-supervised multi-task matching algorithm
      3. 5.4.3 Case analysis
    5. 5.5 DFSSMTAL algorithm
      1. 5.5.1 Mahalanobis distance metric
      2. 5.5.2 Dynamic fuzzy K-nearest neighbour algorithm
      3. 5.5.3 Dynamic fuzzy semi-supervised adaptive learning algorithm
    6. 5.6 Summary
    7. References
  11. 6 Dynamic fuzzy hierarchical relationships
    1. 6.1 Introduction
      1. 6.1.1 Research progress of relationship learning
      2. 6.1.2 Questions proposed
      3. 6.1.3 Chapter structure
    2. 6.2 Inductive logic programming
    3. 6.3 Dynamic fuzzy HRL
      1. 6.3.1 DFL relation learning algorithm (DFLR)
      2. 6.3.2 Sample analysis
      3. 6.3.3 Dynamic fuzzy matrix HRL algorithm
      4. 6.3.4 Sample analysis
    4. 6.4 Dynamic fuzzy tree hierarchical relation learning
      1. 6.4.1 Dynamic fuzzy tree
      2. 6.4.2 Dynamic fuzzy tree hierarchy relationship learning algorithm
      3. 6.4.3 Sample analysis
    5. 6.5 Dynamic fuzzy graph hierarchical relationship learning
      1. 6.5.1 Basic concept of dynamic fuzzy graph
      2. 6.5.2 Dynamic fuzzy graph hierarchical relationship learning algorithm
      3. 6.5.3 Sample analysis
    6. 6.6 Sample application and analysis
      1. 6.6.1 Question description
      2. 6.6.2 Sample analysis
    7. 6.7 Summary
    8. References
  12. 7 Multi-agent learning model based on dynamic fuzzy logic
    1. 7.1 Introduction
      1. 7.1.1 Strategic classification of the agent learning method
      2. 7.1.2 Characteristics of agent learning
      3. 7.1.3 Related work
    2. 7.2 Agent mental model based on DFL
      1. 7.2.1 Model structure
      2. 7.2.2 Related axioms
      3. 7.2.3 Working mechanism
    3. 7.3 Single-agent learning algorithm based on DFL
      1. 7.3.1 Learning task
      2. 7.3.2 Immediate return single-agent learning algorithm based on DFL
      3. 7.3.3 Q-learning function based on DFL
      4. 7.3.4 Q-learning algorithm based on DFL
    4. 7.4 Multi-agent learning algorithm based on DFL
      1. 7.4.1 Multi-agent learning model based on DFL
      2. 7.4.2 Cooperative multi-agent learning algorithm based on DFL
      3. 7.4.3 Competitive multi-agent learning algorithm based on DFL
    5. 7.5 Summary
    6. References
  13. 8 Appendix
    1. 8.1 Dynamic fuzzy sets
      1. 8.1.1 Definition of dynamic fuzzy sets
      2. 8.1.2 Operation of dynamic fuzzy sets
      3. 8.1.3 Cut set of dynamic fuzzy sets
      4. 8.1.4 Dynamic fuzzy sets decomposition theorem
    2. 8.2 Dynamic fuzzy relations
      1. 8.2.1 The conception dynamic fuzzy relations
      2. 8.2.2 Property of dynamic fuzzy relations
      3. 8.2.3 Dynamic fuzzy matrix
    3. 8.3 Dynamic fuzzy logic
      1. 8.3.1 Dynamic fuzzy Boolean variable
      2. 8.3.2 DF proposition logic formation
    4. 8.4 Dynamic fuzzy lattice and its property
  14. Index

Product information

  • Title: Dynamic Fuzzy Machine Learning
  • Author(s): Fanzhang Li, Li Zhang, Zhao Zhang
  • Release date: December 2017
  • Publisher(s): De Gruyter
  • ISBN: 9783110518757