Artificial Evolution

Name: Artificial Evolution | 13th International Conference, Évolution Artificielle, EA 2017, Paris, France, October 25-27, 2017, Revised Selected Papers
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

13th International Conference, Évolution Artificielle, EA 2017, Paris, France, October 25-27, 2017, Revised Selected Papers

Evelyne Lutton Pierrick Legrand Pierre Parrend Nicolas Monmarché Marc Schoenauer(Herausgeber*in)

Springer (Verlag)

Erschienen am 22. März 2018

XVI, 231 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-319-78133-4 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Évolution Artificielle 2017 - EA 2017
Abstracts of Invited Talks
The Cartography of Computational Search Spaces
Progressive Data Analysis: A New Computation Paradigm for Scalability in Exploratory Data Analysis
Contents
On the Design of a Master-Worker Adaptive Algorithm Selection Framework
1 Introduction
2 Related Works
2.1 Sequential Adaptive Algorithm Selection
2.2 Parallel Adaptive Algorithm Selection
2.3 Benchmarks: The Fitness Cloud Model
3 M/W Framework Description
3.1 Aggregation of Local Reward Values
3.2 Homogeneous vs. Heterogeneous Adaptive Selection
4 Experimental Analysis
4.1 Overall Relative Performance
4.2 Analysis of the Reward Aggregation Functions
4.3 Analysis of the Heterogeneity Scenarios
5 Conclusions
References
Comparison of Acceptance Criteria in Randomized Local Searches
1 Introduction
2 Literature Review
3 Experimental Setup
4 Experiments on the Quadratic Assignment Problem
5 Experiments on the Permutation Flow-Shop Problem
6 Conclusions
References
A Fitness Landscape View on the Tuning of an Asynchronous Master-Worker EA for Nuclear Reactor Design
1 Introduction
2 Preliminaries
2.1 Evolutionary Optimization for Nuclear Energy Problems
2.2 Parallel Evolutionary Algorithms
2.3 Landscape Aware Parameter Tuning
3 Problem Definition
3.1 Description of the System
3.2 Criterion of Interest
4 Asynchronous Parallel EA
4.1 Algorithm Definition
4.2 Mutation Operator
5 Experimental Analysis
5.1 Baseline Parameters Setting
5.2 Impact of the Mutation Parameters
5.3 Fitness Landscape Analysis
6 Conclusions
References
Sampled Walk and Binary Fitness Landscapes Exploration
1 Introduction
2 Fitness Landscapes
3 Partial Neighborhood Local Searches
4 Analysis on Binary Fitness Landscapes
4.1 Experimental Protocol
4.2 Results
4.3 Landscapes Ruggedness and Partial Neighborhood LS Efficiency
5 Conclusion
References
Semantics-Based Crossover for Program Synthesis in Genetic Programming
1 Introduction
2 Related Work
2.1 Semantics
2.2 Semantic Crossover
3 Semantics in Program Synthesis
3.1 Semantic Similarity Measure with Traces
3.2 Semantic Crossover for Program Synthesis
4 Experimental Setup
4.1 Benchmark Problems
5 Results
5.1 Successful Runs and Fitness
5.2 Parent Comparison
5.3 Types Selected for Similarity Measurement
6 Conclusion and Future Work
References
On the Use of Dynamic GP Fitness Cases in Static and Dynamic Optimisation Problems
1 Introduction
2 Related Work
2.1 Fitness Cases in Genetic Programming
2.2 Promoting and Maintaining Diversity
3 Proposed Approaches
3.1 Dynamic Fitness Cases
3.2 Kendall Tau Distance
4 Experimental Setup
5 Results and Discussion
5.1 Performance on a Static Setting
5.2 Performance on a Dynamic Setting
5.3 Analysis of the Number of Created Individuals
5.4 Size of GP Programs
6 Conclusions
References
MEMSA: A Robust Parisian EA for Multidimensional Multiple Sequence Alignment
1 Introduction
1.1 Multiple Sequence Alignment (MSA)
1.2 Evolutionary Algorithms for MSA
1.3 Parisian Evolution Approach
2 Genetic Algorithm with Parisian Approach for MSA
2.1 Individuals/Patches
2.2 Initialisation
2.3 Crossover
2.4 Mutator
2.5 Evaluation
2.6 Diversity Preservation
2.7 Selection of Individuals for the New Generation
2.8 Patchwork to Create an MSA
2.9 Run Parameters and Behaviour of the Algorithm
3 Experiments and Validation
4 Discussion and Conclusion
References
Basic, Dual, Adaptive, and Directed Mutation Operators in the Fly Algorithm
1 Introduction
2 Problem Definition and Motivations
3 Overview of the Fly Algorithm for PET Reconstruction
4 Varying Mutation Operators in the Fly Algorithm
4.1 Basic Mutation
4.2 Adaptive Mutation Variance
4.3 Dual Mutation
4.4 Directed Mutation
5 Results
6 Conclusion
References
A New High-Level Relay Hybrid Metaheuristic for Black-Box Optimization Problems
1 Introduction
2 Presentation of the Hybridized Components
2.1 Overview of MLSDO Algorithm
2.2 Overview of SHADE Algorithm
2.3 Overview of SPSO2011 Algorithm
3 The Proposed Hybrid Algorithm
4 Experimental Protocol and Parameter Setting
4.1 The BBOB 2015 Benchmark
4.2 The Black Box Optimization Competition
4.3 Parameter Setting
5 Experimental Results and Discussion
5.1 Results for the BBOB 2015 Benchmark
5.2 Results at the Black Box Optimization Competition
6 Conclusion
References
Improved Hybrid Iterative Tabu Search for QAP Using Distance Cooperation
1 Introduction
2 Background
3 Distributed and Cooperative Algorithms
3.1 Distributed Hybrid Iterative Tabu Search
3.2 Distance Cooperation Hybrid Iterative Tabu Search
4 Experimental Results
4.1 Platform and Tests
4.2 Parameters
4.3 Experimentation
4.4 Literature Comparison
5 Conclusion and Perspectives
References
H-ACO: A Heterogeneous Ant Colony Optimisation Approach with Application to the Travelling Salesman Problem
1 Introduction
2 Ant Colony Optimization
3 Heterogeneous ACO
4 Methodology
4.1 Travelling Salesman Problem bib2
5 Experimental Setup
6 Heterogeneous ACO Results
6.1 Exploring the Ranges of Alpha and Beta
6.2 Comparison with Base Algorithms
7 Discussion, Conclusion and Future Work
References
Evolutionary Learning of Fire Fighting Strategies
1 Introduction
2 Fire Enclosement in a Discrete Grid Setting
2.1 A Goal Oriented Evolution Model
2.2 Evolutionary Algorithm
2.3 Experimental Results
2.4 Fire Enclosement Conclusion
3 Protection of a Highway
3.1 Evolution Models
3.2 Evolutionary Algorithm
3.3 Experimental Results
3.4 Highway Protection Conclusion
4 Future Work on Theoretical Threshold Questions
References
Evolutionary Optimization of Tone Mapped Image Quality Index
1 Introduction
2 Related Work
3 Algorithm
3.1 Tone Mapping
3.2 Evolutionary Optimization
4 Experimental Results
5 Conclusion
References
LIDeOGraM: An Interactive Evolutionary Modelling Tool
1 Introduction
2 Background
2.1 Food Complex Systems
2.2 Symbolic Regression
2.3 Production and Stabilisation Process of Lactic Acid Bacteria
3 Proposed Approach
4 Experimental Results
4.1 The Dataset
4.2 Search with Eureqa
4.3 Optimisation of the Global Model
5 Discussion
6 Conclusions
References
Automatic Configuration of GCC Using Irace
1 Introduction
2 Automatic Algorithm Configuration
3 Configuration Scenarios
4 GCC Configuration Scenarios Analysis
5 Experimental Results
6 Conclusion and Future Work
References
Offline Learning for Selection Hyper-heuristics with Elman Networks
1 Introduction
2 Methodology
2.1 HyFlex and the Offline Learning Database
2.2 Final Log Returns and the BEST Sequences
2.3 Elman Networks
2.4 Training Sets
2.5 The BLIND Hyper-heuristic
3 Results
3.1 Network Training
3.2 Evaluating the Elman Network Sequences
4 Conclusions
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken