| Description |
1 online resource |
| Contents |
Intro; Preface; References; Acknowledgements; Contents; 1 Introduction; 1.1 Evolution at Work; 1.2 Have We Solved the Problem of the Evolution of the Eye, Which Troubled Darwin?; 1.3 Evolutionary Algorithms: From Bullet Trains to Finance and Robots; 1.4 Genetic Programming and Its Genome Representation; 1.4.1 Tree-Based Representation of Genetic Programming; 1.4.2 Linear Genetic Programming; 1.5 Cartesian Genetic Programming (CGP)sym]CGP; 1.6 Interactive Evolutionary Computation (IEC); 1.7 Why Evolutionary Computation?; References |
|
2 Meta-heuristics, Machine Learning, and Deep Learning Methods2.1 Meta-heuristics Methodologies; 2.1.1 PSO: Particle Swarm Optimization; 2.1.2 DE: Differential Evolution; 2.2 Machine Learning Techniques; 2.2.1 k-Means Algorithm; 2.2.2 SVM; 2.2.3 RVM: Relevance Vector Machine; 2.2.4 k-Nearest Neighbor Classifier; 2.2.5 Transfer Learning; 2.2.6 Bagging and Boosting; 2.2.7 Gröbner Bases; 2.2.8 Affinity Propagation and Clustering Techniques; 2.3 Deep Learning Frameworks; 2.3.1 CNN and Feature Extraction; 2.3.2 Generative Adversary Networks (GANsym]GAN) and Generating Fooling Images |
|
2.3.3 Bayesian Networks and Loopy Belief PropagationReferences; 3 Evolutionary Approach to Deep Learning; 3.1 Neuroevolution; 3.1.1 NEAT and HyperNEAT; 3.1.2 CPPN and Pattern Generation; 3.2 Deep Neural Networks with Evolutionary Optimization; 3.2.1 Genetic Convolutional Neural Networks (Genetic CNNs); 3.2.2 Hierarchical Feature Construction Using GP; 3.2.3 Differentiable Pattern-Producing Network; References; 4 Machine Learning Approach to Evolutionary Computation; 4.1 BagGP and BoostGP; 4.2 Vanishing Ideal GP: Algebraic Approach to GP; 4.2.1 Symbolic Regression and GP |
|
4.2.2 Vanishing Ideal4.2.3 VIGP: Reduction Process; 4.2.4 VIGP Versus GP Comparison; 4.2.5 VIGP for Rational Polynomials; 4.2.6 VIGP for the 6-Parity Problem; 4.3 The Kaizen Programming; 4.4 RVM-GP: RVM for Automatic Feature Selection in GP; 4.4.1 The Sequential Sparse Bayesian Learning Algorithm; 4.4.2 Model Selection in RVM-GP; 4.4.3 RVM-GP Performance; 4.5 PSOAP: Particle Swarm Optimization Based on Affinity Propagation; 4.6 Machine Learning for Differential Evolution; 4.6.1 ILSDE; 4.6.2 SVC-DE; 4.6.3 TRADE: TRAnsfer Learning for DE; 4.6.4 NENDE: k-NN Classifier for DE; References |
|
5 Evolutionary Approach to Gene Regulatory Networks5.1 Overview of Gene Regulatory Networks; 5.2 GRN Inference by Evolutionary and Deep Learning Methods; 5.2.1 Inferring Genetic Networks; 5.2.2 INTERNe: IEC-Based GRN Inference with ERNe; 5.3 MONGERN: GRN Application for Humanoid Robots; 5.3.1 Evolutionary Robotics and GRN; 5.3.2 How to Express Motions; 5.3.3 How to Learn Motions; 5.3.4 How to Make Robust Motions; 5.3.5 Simulation Experiments with MONGERN; 5.3.6 Real Robot Experiments with MONGERN; 5.3.7 Robustness with MONGERN; 5.4 ERNe: A Framework for Evolving Reaction Networks |
| Summary |
This book provides theoretical and practical knowledge about a methodology for evolutionary algorithm-based search strategy with the integration of several machine learning and deep learning techniques. These include convolutional neural networks, Gröbner bases, relevance vector machines, transfer learning, bagging and boosting methods, clustering techniques (affinity propagation), and belief networks, among others. The development of such tools contributes to better optimizing methodologies. Beginning with the essentials of evolutionary algorithms and covering interdisciplinary research topics, the contents of this book are valuable for different classes of readers: novice, intermediate, and also expert readers from related fields. Following the chapters on introduction and basic methods, Chapter 3 details a new research direction, i.e., neuro-evolution, an evolutionary method for the generation of deep neural networks, and also describes how evolutionary methods are extended in combination with machine learning techniques. Chapter 4 includes novel methods such as particle swarm optimization based on affinity propagation (PSOAP), and transfer learning for differential evolution (TRADE), another machine learning approach for extending differential evolution. The last chapter is dedicated to the state of the art in gene regulatory network (GRN) research as one of the most interesting and active research fields. The author describes an evolving reaction network, which expands the neuro-evolution methodology to produce a type of genetic network suitable for biochemical systems and has succeeded in designing genetic circuits in synthetic biology. The author also presents real-world GRN application to several artificial intelligent tasks, proposing a framework of motion generation by GRNs (MONGERN), which evolves GRNs to operate a real humanoid robot |
| Bibliography |
Includes bibliographical references and indexes |
| Notes |
Online resource; title from PDF title page (SpringerLink, viewed June 19, 2018) |
| Subject |
Machine learning.
|
|
Neural networks (Computer science)
|
|
Evolutionary computation.
|
|
Neural Networks, Computer
|
|
Machine Learning
|
|
Molecular biology.
|
|
Maths for scientists.
|
|
Artificial intelligence.
|
|
COMPUTERS -- General.
|
|
Evolutionary computation
|
|
Machine learning
|
|
Neural networks (Computer science)
|
| Form |
Electronic book
|
| ISBN |
9789811302008 |
|
9811302006 |
|
