Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben

2019 | Buch

Introduction to Evolutionary Single-Objective Optimisation Kapitel lesen Erstes Kapitel lesen

Evolutionary Algorithms and Neural Networks

Theory and Applications

verfasst von: Dr. Seyedali Mirjalili

Verlag: Springer International Publishing

Buchreihe : Studies in Computational Intelligence

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

This book introduces readers to the fundamentals of artificial neural networks, with a special emphasis on evolutionary algorithms. At first, the book offers a literature review of several well-regarded evolutionary algorithms, including particle swarm and ant colony optimization, genetic algorithms and biogeography-based optimization. It then proposes evolutionary version of several types of neural networks such as feed forward neural networks, radial basis function networks, as well as recurrent neural networks and multi-later perceptron. Most of the challenges that have to be addressed when training artificial neural networks using evolutionary algorithms are discussed in detail. The book also demonstrates the application of the proposed algorithms for several purposes such as classification, clustering, approximation, and prediction problems. It provides a tutorial on how to design, adapt, and evaluate artificial neural networks as well, and includes source codes for most of the proposed techniques as supplementary materials.

Inhaltsverzeichnis

Frontmatter

Evolutionary Algorithms

Frontmatter
Chapter 1. Introduction to Evolutionary Single-Objective Optimisation
Abstract
This chapter provides preliminaries and essential definitions in the field of single-objective optimisation. Several difficulties that an optimisation algorithm might face when training Neural Networks are discussed as well.
Seyedali Mirjalili
Chapter 2. Particle Swarm Optimisation
Abstract
This chapter covers the the inspiration, mathematical model, and main mechanisms of the Particle Swarm Optimisation (PSO). The binary version of this algorithm (BPSO) is also presented. Several experiments are conducted to analyze the performance of both PSO and BPSO qualitatively and quantitatively.
Seyedali Mirjalili
Chapter 3. Ant Colony Optimisation
Abstract
Ant Colony Optimisation (ACO) is one of the well-known swarm intelligence techniques in the literature. This chapter discusses the inspiration and mathematical model of several valiants of this algorithm. To analyse the performance of ACO, it is applied to several Travailing Salesman Problem (TSP).
Seyedali Mirjalili
Chapter 4. Genetic Algorithm
Abstract
Genetic Algorithm (GA) is one of the first population-based stochastic algorithm proposed in the history. Similar to other EAs, the main operators of GA are selection, crossover, and mutation. This chapter briefly presents this algorithm and applies it to several case studies to observe its performance.
Seyedali Mirjalili
Chapter 5. Biogeography-Based Optimisation
Abstract
Biogeography-Based Optimisation (BBO) [1] is one of the recent evolutionary algorithms with successful application in a diverse field of studies. Similarly to other evolutionary algorithms, BBO has been equipped with crossover and mutations. The main difference between this algorithm and GA is the use of two operators to perform crossover and exploitation. The concepts of mutation is also similar, in which small changes occur in variables of solutions. However, each solution in BBO faces different mutation rates depending on its fitness, which makes it different from the GA algorithm. In this chapter, the inspiration and mathematical equations of the BBO algorithm are first given. A set of problems is then solved with this algorithm to observe and analyse its performance.
Seyedali Mirjalili

Evolutionary Neural Networks

Frontmatter
Chapter 6. Evolutionary Feedforward Neural Networks
Abstract
Feedforward Neural Networks (FNN) have been of the most popular NNs with a wide range of applications. The process of finding optimal values for controlling parameters of a NN is called training and can be considered as an optimisation problem. This chapter trains FNNs using several optimisation algorithms.
Seyedali Mirjalili
Chapter 7. Evolutionary Multi-layer Perceptron
Abstract
This chapter trains Multi-Later Perceptron (MLP) using several optimisation algorithms. A set of test and real-world case studies is employed to compare the proposed evolutionary trainers.
Seyedali Mirjalili
Chapter 8. Evolutionary Radial Basis Function Networks
Abstract
Radial Basis Function (RBF) networks are one of the most popular and applied type of neural networks. RBF networks are universal approximators and considered as special form of multilayer feedforward neural networks that contain only one hidden layer with Gaussian based activation functions. This chapter trains such NNs with several optimisation algorithms and compares their performance.
Seyedali Mirjalili
Chapter 9. Evolutionary Deep Neural Networks
Abstract
This chapter first employs a kinematic model of hand to create two datasets for static hand postures. Neural Networks with different learning algorithms are then applied to the datasets for classification. The chapter also considers the comparison and analysis of different evolutionary algorithms for classifying datasets as well. Another contribution is finding the best set of features for the dataset using evolutionary algorithms. The results show that due to the large number of samples and features, Back Propagation is not effective due to the problem of local optima stagnation. However, Evolutionary Algorithms are able to efficiently classify the dataset with a very high accuracy and convergence speed. It was also observed that feature selection is important and evolutionary algorithms are able to find the optimal set of features for this problem.
Seyedali Mirjalili
Metadaten
Titel
Evolutionary Algorithms and Neural Networks
verfasst von
Dr. Seyedali Mirjalili
Copyright-Jahr
2019
Electronic ISBN
978-3-319-93025-1
Print ISBN
978-3-319-93024-4
DOI
https://doi.org/10.1007/978-3-319-93025-1

Premium Partner

    Bildnachweise