Genetic Programming Theory and Practice XV

Name: Genetic Programming Theory and Practice XV
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

Wolfgang Banzhaf Randal S. Olson William Tozier Rick Riolo(Herausgeber*in)

Springer (Verlag)

1. Auflage

Erschienen am 5. Juli 2018

XV, 187 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-319-90512-9 (ISBN)

96,29 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Foreword
Preface
Acknowledgements
Contents
Contributors
1 Exploiting Subprograms in Genetic Programming
1.1 Introduction
1.2 Related Work
1.3 Exploiting Subprograms
1.3.1 BGP Strategy
1.3.2 Exploring Model Bias
1.3.3 Identifying Useful Subprograms
1.4 Experiments
1.4.1 Experimental Data, Parameters
1.4.2 Sensitivity to Model Bias
1.4.3 Aggregate Trace Matrices
1.5 Conclusions and Future Work
References
2 Schema Analysis in Tree-Based Genetic Programming
2.1 Introduction
2.1.1 Diversity and Evolutionary Dynamics
2.1.2 Genetic Programming Schemata
2.2 Methodology
2.2.1 Schema Generation
2.2.2 Schema Matching
2.3 Experimental Setup
2.3.1 Algorithm Parameters
2.3.2 Problem Instances
2.3.3 Analysis Methods
2.4 Empirical Results
2.4.1 Standard GP
Poly-10 Problem
Tower Problem
2.4.2 Offspring Selection GP
Poly-10 Problem
2.5 Conclusion
References
3 Genetic Programming Symbolic Classification: A Study
3.1 Introduction
3.2 AMAXSC in Brief
3.3 MDC in Brief
3.4 M2GP in Brief
3.5 LDA Background
3.6 LDA Matrix Math
3.7 LDA Assisted Fitness Implementation
3.7.1 Converting to Basis Space
3.7.2 Class Clusters and Centroids
3.7.3 LDA Coefficients
3.8 Artificial Test Problems
3.9 Performance on Test Problems
3.10 Conclusion
References
4 Problem Driven Machine Learning by Co-evolving Genetic Programming Trees and Rules in a Learning Classifier System
4.1 Introduction
4.2 Methods
4.2.1 ExSTraCS
4.2.2 GP Integration
4.2.2.1 GP Population Initialization
4.2.2.2 GP Parent Selection
4.2.2.3 GP Mating
4.2.2.4 GP Fitness and Evaluation
4.2.3 Datasets and Evaluation
4.3 Preliminary Results
4.4 Conclusions and Ongoing Work
References
5 Applying Ecological Principles to Genetic Programming
5.1 Introduction
5.1.1 Motivation
5.1.2 Ecological Approaches in Evolutionary Algorithms
5.1.3 Limited Resources and Eco-EA
5.1.4 Complexifying Environments
5.2 Methods
5.2.1 10-Dimensional Box Problem
5.2.2 Eco-EA Implementation
5.2.3 Lexicase Selection Implementation
5.2.4 Tournament Selection Implementation
5.2.5 Configuration Details
5.2.6 Statistical Methods
5.2.7 Code Availability
5.3 Results and Discussion
5.4 Conclusions and Future Work
References
6 Lexicase Selection with Weighted Shuffle
6.1 Introduction
6.2 Lexicase Selection
6.3 Weighted Shuffle
6.3.1 Shuffling Methods
6.3.2 Bias Metrics
6.4 Experimental Setup
6.4.1 Problems
6.4.2 Push and PushGP
6.5 Results
6.6 Discussion
6.7 Related Work
6.8 Conclusions and Future Work
References
7 Relaxations of Lexicase Parent Selection
7.1 Introduction
7.2 Lexicase Selection
7.3 Epsilon Lexicase Selection
7.4 Random Threshold Lexicase Selection
7.5 MADCAP Epsilon Lexicase Selection
7.6 Truncated Lexicase Selection
7.7 Experimental Results
7.8 Relation to Many-Objective Optimization
7.9 Discussion
References
8 A System for Accessible Artificial Intelligence
8.1 Introduction
8.2 The Human Engine
8.3 The Human-Computer Interaction Engine
8.4 The Machine Learning Engine
8.5 The Controller Engine
8.6 The Graph Database Engine
8.6.1 Knowledge Base
8.7 The Artificial Intelligence Engine
8.8 The Visualization Engine
8.9 Discussion and Future Work
References
9 Genetic Programming Based on Error Decomposition: A Big Data Approach
9.1 Introduction
9.2 Computational Model
9.3 Case Study
9.4 Performance Analysis
9.5 Conclusions
References
10 One-Class Classification of Low Volume DoS Attacks with Genetic Programming
10.1 Introduction
10.2 Our Method
10.2.1 Intuition
10.2.2 Formal Definition
10.2.3 Ensemble Formation
10.3 Related Work
10.4 Experiments
10.4.1 Datasets
10.4.1.1 KDD Cup Dataset
10.4.1.2 NSL-KDD Dataset
10.4.1.3 Proprietary Dataset
10.4.2 Genetic Programming Parameters
10.4.3 Comparison Algorithm
10.4.4 Classification Results
10.4.5 Selection of GP Models and Ensemble Classifier
10.5 Conclusion
References
11 Evolution of Space-Partitioning Forest for Anomaly Detection
11.1 Anomaly Detection for Streaming Data
11.2 Analysis of Random Trees
11.2.1 Number of Nodes Needed to Capture Anomaly Characteristics
11.2.1.1 Theoretical Justification
11.2.1.2 Experimental Results
11.2.2 Number and Height of Trees
11.2.2.1 The Coupon Collector's Problem: Analysis of Tree Height
11.2.2.2 Number of Trees T for a Given Tree Height h and Number of Features d
11.3 Use EA to Better Partition Data Space
11.3.1 How to Partition the Data Space to Separate Outliers
11.3.2 Space-Partitioning Forest
11.3.3 Individual Representation
11.3.4 Cost Function
11.3.5 Mutation
11.3.6 Crossover
11.3.7 Selection
11.3.8 Algorithms
11.3.9 Preliminary Results for EA
11.4 Conclusion and Future Work
References
Index

Systemvoraussetzungen

Als PDF speichern Als Link merken