This book focuses on both theory and application of evolutionary algorithms and artificial neural networks. An attempt is made to make a bridge between these two fields with an emphasis on real-world applications.
Part I presents well-regarded and recent evolutionary algorithms and optimisation techniques. Quantitative and qualitative analyses of each algorithm are performed to understand the behaviour and investigate their potentials to be used in conjunction with artificial neural networks.
Part II reviews the literature of several types of artificial neural networks including feedforward neural networks, multi-layer perceptrons, and radial basis function network. It then proposes evolutionary version of these techniques in several chapters. Most of the challenges that have to be addressed when training artificial neural networks using evolutionary algorithms are discussed in detail.
Due to the simplicity of the proposed techniques and flexibility, readers from any field of study can employ them for classification, clustering, approximation, and prediction problems. In addition, the book demonstrates the application of the proposed algorithms in several fields, which shed lights to solve new problems. The book provides a tutorial on how to design, adapt, and evaluate artificial neural networks as well, which would be beneficial for the readers interested in developing learning algorithms for artificial neural networks.
Part I. Evolutionary Algorithms
1. Introduction to Evolutionary Single-Objective Optimisation
2. Particle Swarm Optimisation
3. Ant Colony Optimisation
4. Genetic Algorithm
5. Biogeography-Based Optimisation
Part II. Evolutionary Neural Networks
6. Evolutionary Feedforward Neural Networks
7. Evolutionary Multi-layer Perceptron
8. Evolutionary Radial Basis Function Networks
9. Evolutionary Deep Neural Networks
Enlaces Públicos de descarga