Genetic Programming

Name: Genetic Programming | 22nd European Conference, EuroGP 2019, Held as Part of EvoStar 2019, Leipzig, Germany, April 24-26, 2019, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

22nd European Conference, EuroGP 2019, Held as Part of EvoStar 2019, Leipzig, Germany, April 24-26, 2019, Proceedings

Lukas Sekanina Ting Hu Nuno Lourenço Hendrik Richter Pablo García-Sánchez(Editor)

Springer (Publisher)

Published on 10. April 2019

XII, 295 pages

E-Book

PDF with digital watermarking

System requirements

978-3-030-16670-0 (ISBN)

€53.49incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Intro
Preface
Organization
Contents
Long Presentations
Ariadne: Evolving Test Data Using Grammatical Evolution
1 Introduction
2 Background and Related Work
2.1 Related Work
2.2 Grammatical Evolution
3 GE Based Test Data Generation-Ariadne
3.1 Overview
3.2 Grammar
3.3 Fitness Function
4 Experimental Results and Discussion
4.1 Test Functions
4.2 Experimental Setup
4.3 Detailed Analysis of Experiments
5 Conclusion and Future Work
References
Quantum Program Synthesis: Swarm Algorithms and Benchmarks
1 Introduction
2 Quantum Computation Using the Circuit Model
3 Ant Programming
4 Quantum Ant Programming
4.1 Elitism and Pseudo-elitism
4.2 Controllable Gates
4.3 Parameters
4.4 Randomized Quantum Ant Programming (R-QAP)
5 Fitness of a Quantum Circuit: Mean Square Fidelity
6 Benchmark Problems
7 Experiments
7.1 Results
8 Conclusion
References
A Genetic Programming Approach to Predict Mosquitoes Abundance
1 Introduction
2 Data Set
3 Classical Statistical Approach
4 Application of GP
4.1 Experimental Setting
4.2 Experimental Results
5 Comparison with the Statistical Model
6 Discussion
7 Conclusion
References
Complex Network Analysis of a Genetic Programming Phenotype Network
1 Introduction
2 Methods
2.1 A Boolean Linear Genetic Programming Algorithm
2.2 Genotype, Phenotype, and Fitness
2.3 Phenotype Networks
2.4 Complex Network Analysis
3 Results
3.1 Sampled Genotype Space and Mutational Connections
3.2 Properties of the Undirected Weighted Phenotype Network
3.3 Communities in the Undirected Weighted Phenotype Network
3.4 Random Walks
3.5 In-degree and Out-degree in the Directed Phenotype Networks
3.6 Fitness Correlation of Neighboring Phenotypes
4 Discussion
References
Improving Genetic Programming with Novel Exploration - Exploitation Control
1 Introduction
2 Background
2.1 Grammar Based Genetic Programming
2.2 Program Synthesis
2.3 Search Convergence
3 Method
3.1 Our Distance Measures
3.2 How We Measure Novelty
3.3 Knobelty Selection
4 Experiments
4.1 Setup
4.2 Results
5 Conclusions and Future Work
References
Towards a Scalable EA-Based Optimization of Digital Circuits
1 Introduction
2 Background
2.1 Boolean Networks
2.2 Limiting the Scope of Boolean Networks
2.3 Evolutionary Synthesis of Logic Circuits
3 The Proposed Method
4 Experimental Evaluation
4.1 Experimental Setup
4.2 Experimental Results
5 Conclusion
References
Cartesian Genetic Programming as an Optimizer of Programs Evolved with Geometric Semantic Genetic Programming
1 Introduction
2 Relevant Work
2.1 Geometric Semantic Genetic Programming
2.2 Cartesian Genetic Programming
3 Subtree CGP
3.1 Obtaining the CGP Representation
3.2 CGP-based Optimization of Subtrees
3.3 Subtree Pairing
4 Results
4.1 Data Sets
4.2 Obtaining Reference Solutions with GSGP
4.3 Experiments with SCGP
4.4 Final Results
4.5 Discussion
5 Conclusions
References
Can Genetic Programming Do Manifold Learning Too?
1 Introduction
1.1 Goals
2 Background
2.1 Dimensionality Reduction
2.2 Manifold Learning
2.3 Related Work
3 GP for Manifold Learning (GP-MaL)
3.1 GP Representation
3.2 Fitness Function
3.3 Tackling the Computational Complexity
4 Experiment Design
5 Results and Analysis
5.1 GP-MaL Compared to PCA & MDS
5.2 GP-MaL Compared to LLE & T-SNE
5.3 Summary
6 Further Analysis
6.1 GP-MaL for Data Visualisation
6.2 Tree Interpretability
7 Conclusion
References
Why Is Auto-Encoding Difficult for Genetic Programming?
1 Introduction
2 Related Work
3 Proposed Model
3.1 Linear GP for Multi-output Regression
3.2 From Programs to Pairs of Programs
3.3 Step-Counting Hill-Climbing
4 Experiments and Results
4.1 Datasets
4.2 Experimental Design
4.3 Results: Autoencoding Experiments
4.4 Results: Regression with Multiple Distinct Outputs
4.5 Results: Regression with Multiple Identical Outputs
4.6 Results: Regression with a Single Output
4.7 Discussion and Limitations
5 Conclusions and Future Work
References
Solution and Fitness Evolution (SAFE): Coevolving Solutions and Their Objective Functions
1 Objective = Objective Function
2 Related Work
3 Novelty Search
4 Coevolution
5 The Robot and the Maze
6 SAFE: Solution and Fitness Evolution
7 Results
8 Discussion and Concluding Remarks
References
A Model of External Memory for Navigation in Partially Observable Visual Reinforcement Learning Tasks
1 Introduction
2 Background
3 Tangled Program Graphs
3.1 Bid-Based GP
3.2 Coevolution of GP Teams
3.3 Evolving Graphs of Teams of Programs
4 Memory Model
5 Empirical Evaluation
5.1 Parameterization
5.2 Results
6 Conclusions
References
Fault Detection and Classification for Induction Motors Using Genetic Programming
1 Introduction
2 Methods
2.1 Experiments and Data Collection for Induction Motor Faults
2.2 Signal Processing and Feature Extraction
2.3 Multi-label Classification by Linear Genetic Programming
2.4 Experiment Setup
3 Results
3.1 Best Evolved Classification Models
3.2 Feature Importance Assessment
3.3 Comparison with Other Machine Learning Algorithms
4 Discussion
References
Short Presentations
Fast DENSER: Efficient Deep NeuroEvolution
1 Introduction
2 Related Work
3 DENSER
4 Fast DENSER
4.1 Representation
4.2 Initialisation
4.3 Genetic Operators
4.4 Evolution
4.5 Evaluation
5 Experimentation
5.1 Experimental Setup
5.2 Statistical Analysis
5.3 Experimental Results
6 Conclusions and Future Work
References
A Vectorial Approach to Genetic Programming
1 Introduction
2 Previous and Related Work
3 Vectorial GP
4 Experiments
4.1 Benchmark Problems
4.2 Parameters and Statistical Test
5 Results
6 Discussion
7 Conclusion
References
Comparison of Genetic Programming Methods on Design of Cryptographic Boolean Functions
1 Introduction
2 Preliminaries
2.1 Use of Boolean Functions
2.2 Property Definitions
3 Genetic Programming Methods
3.1 Related Works
4 Objectives
4.1 Experimental Setup
4.2 Parameter Optimization
5 Results
6 Conclusion and Future Work
References
Evolving AVX512 Parallel C Code Using GP
1 Background: RNA, Genetic Improvement and RNAfold
1.1 RNA_STRAND
1.2 GGGP Genetic Improvement System
1.3 Parallel SSE 128-Bit and AVX 512-Bit Vector Instructions
2 The Grammar Based Genetic Programming System
2.1 Representation: Variable Length Genome
2.2 BNF Generic Vector Types veci (m128i, m256i or m512i)
2.3 veci Mutations: Switching Between m128i, m256i or m512i
2.4 BNF Grammar Type Matching
2.5 Vector Type Matching Rules
2.6 Population Size
2.7 Initial Population
2.8 Genetic Operations: Mutation and Crossover
2.9 Compiling Gcc -O2 -DNDEBUG -march=native -mtune=native
2.10 Fitness Function: Run 10000 Times, Elapsed Time and Accuracy
2.11 Selection for Speed and Correctness
2.12 10 Member Elite
3 Results
3.1 Evolving the Population
3.2 Choosing the Winner
3.3 Explaining the Wining Evolved Program
3.4 Improved Performance Inside RNAfold
3.5 Performance on Hold Out Data
4 Discussion: Population Convergence
5 Conclusions
References
Hyper-bent Boolean Functions and Evolutionary Algorithms
1 Introduction
2 Background
3 Related Work
4 Experimental Setup
4.1 Truth Table Representation
4.2 Tree Representation
4.3 Boolean Construction Representation
4.4 Fitness Functions
5 Experiments
5.1 Results
5.2 Future Work
6 Conclusions
References
Learning Class Disjointness Axioms Using Grammatical Evolution
1 Introduction
2 Related Work
3 Background
3.1 RDF Datasets
3.2 OWL 2 Axioms
4 A Grammatical Evolution Approach to Discovering OWL 2 Axioms
4.1 Representation
4.2 Initialization
4.3 Parent Selection
4.4 Variation Operators
4.5 Survival Selection
4.6 Fitness Evaluation
5 Experiment and Result
6 Conclusion and Future Work
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Genetic Programming

Description

More details

Other editions

Additional editions

Content

System requirements