Muutke küpsiste eelistusi

E-raamat: Swarm Intelligence and Evolutionary Computation: Theory, Advances and Applications in Machine Learning and Deep Learning [Taylor & Francis e-raamat]

Edited by
  • Formaat: 204 pages, 15 Tables, black and white; 2 Line drawings, color; 11 Line drawings, black and white; 1 Halftones, color; 3 Halftones, black and white; 3 Illustrations, color; 14 Illustrations, black and white
  • Ilmumisaeg: 07-Mar-2023
  • Kirjastus: CRC Press
  • ISBN-13: 9781003247746
Teised raamatud teemal:
  • Taylor & Francis e-raamat
  • Hind: 193,88 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 276,97 €
  • Säästad 30%
Swarm Intelligence and Evolutionary Computation: Theory, Advances and Applications in Machine Learning and Deep LearningSuurem pilt
  • Formaat: 204 pages, 15 Tables, black and white; 2 Line drawings, color; 11 Line drawings, black and white; 1 Halftones, color; 3 Halftones, black and white; 3 Illustrations, color; 14 Illustrations, black and white
  • Ilmumisaeg: 07-Mar-2023
  • Kirjastus: CRC Press
  • ISBN-13: 9781003247746
Teised raamatud teemal:
Taylor & Francis e-raamatudRohkem infot Taylor & Francis e-raamatute kohta
Raamatu kodulehekülg: https://www.taylorfrancis.com/books/9781003247746
"The aim of this book is to present and analyze theoretical advances and also emerging practical applications of swarm and evolutionary intelligence. It includes ten relevant chapters. In chapter 1, a theoretical introduction of the computational optimization techniques is provided regarding the gradient based methods such as steepest descent, conjugate gradient, newton and quasi-Newton methods and also the non-gradient methods such as genetic algorithm and swarm intelligence algorithms. In chapter 2, evolutionary computation techniques and genetic algorithm are discussed. In chapter 3, swarm intelligence theory and particle swarm optimization algorithm are discussed. Also, several variations of particle swarm optimization algorithm are analyzed and explained such as Geometric PSO and Quantum mechanics-based PSO Algorithm. In chapter 4, two essential colony bio-inspired algorithms are examined: Ant colony optimization (ACO) and Artificial Bee Colony (ABC). In chapter 5, Cuckoo search and Bat swarm algorithms are presented and analyzed. In chapter 6, several other metaheuristic algorithms are discussed such as: Firefly algorithm (FA), Harmony search (HS), Cat swarm optimization (CSO). The latest Bio-Inspired Swarm Algorithms are discussed in chapter 7, such as: Grey Wolf Optimization (GWO) Algorithm, Whale Optimization Algorithm (WOA), Grasshopper Optimization Algorithm (GOA). Machine learning optimization applications are presented in chapter 8, such as artificial neural network optimization. In chapter 9 an application of swarm intelligence in deep long short-term memory (LSTM) networks is discussed. In chapter 10, an illustrative application of swarm intelligence on Deep CNN satellite image classification regarding the remote sensing of environment is presented. The final scope of the book is to provide knowledge towards the application of improved optimization techniques in several computational and artificial intelligence problems"--

This book aims at providing theoretical knowledge in the application of swarm intelligence and evolutionary computation including several recent meta-heuristic algorithms and also providing practical emerging applications in machine learning and deep learning.



The aim of this book is to present and analyse theoretical advances and also emerging practical applications of swarm and evolutionary intelligence. It comprises nine chapters. Chapter 1 provides a theoretical introduction of the computational optimization techniques regarding the gradient-based methods such as steepest descent, conjugate gradient, newton and quasi-Newton methods and also the non-gradient methods such as genetic algorithm and swarm intelligence algorithms. Chapter 2, discusses evolutionary computation techniques and genetic algorithm. Swarm intelligence theory and particle swarm optimization algorithm are reviewed in Chapter 3. Also, several variations of particle swarm optimization algorithm are analysed and explained such as Geometric PSO, PSO with mutation, Chaotic PSO with mutation, multi-objective PSO and Quantum mechanics – based PSO algorithm. Chapter 4 deals with two essential colony bio-inspired algorithms: Ant colony optimization (ACO) and Artificial bee colony (ABC). Chapter 5, presents and analyses Cuckoo search and Bat swarm algorithms and their latest variations. In chapter 6, several other metaheuristic algorithms are discussed such as: Firefly algorithm (FA), Harmony search (HS), Cat swarm optimization (CSO) and their improved algorithm modifications. The latest Bio-Inspired Swarm Algorithms are discussed in chapter 7, such as: Grey Wolf Optimization (GWO) Algorithm, Whale Optimization Algorithm (WOA), Grasshopper Optimization Algorithm (GOA) and other algorithm variations such as binary and chaotic versions. Chapter 8 presents machine learning applications of swarm and evolutionary algorithms. Illustrative real-world examples are presented with real datasets regarding neural network optimization and feature selection, using: genetic algorithm, Geometric PSO, Chaotic Harmony Search, Chaotic Cuckoo Search, and Evolutionary Algorithm and also crime forecasting using swarm optimized SVM. In chapter 9, applications of swarm intelligence on deep long short-term memory (LSTM) networks and Deep Convolutional Neural Networks (CNNs) are discussed, including LSTM hyperparameter tuning and Covid19 diagnosis from chest X-Ray images. The aim of the book is to present and discuss several state-of-theart swarm intelligence and evolutionary algorithms together with their variances and also several illustrative applications on machine learning and deep learning.
Preface iii
1 Computational optimization
1(18)
Computational optimization
1(1)
Introduction
1(1)
Optimization methods
2(1)
Gauss-Newton method
2(1)
Quasi-Newton method
3(1)
Gradient-based optimization
4(1)
Steepest or gradient descent algorithm
5(1)
Conjugate gradient algorithms
5(2)
Optimizers for machine learning
7(1)
Stochastic gradient descent
7(1)
Stochastic gradient descent with momentum
7(1)
Levenberg-Marquardt algorithm
8(4)
Scaled conjugate gradient algorithm
12(2)
Adagrad
14(1)
RMSProp
15(1)
Adadelta
15(1)
Adam optimizer
16(1)
Non-gradient methods
17(1)
References
17(2)
2 Evolutionary Computation and Genetic Algorithm
19(18)
Evolutionary strategy
19(1)
Genetic algorithm
20(1)
Initialization
21(1)
Selection methods
21(1)
Tournament selection
22(1)
Linear ranking selection
22(1)
Proportionate roulette wheel selection
22(1)
Exponential ranking selection
23(1)
Crossover (recombination) operators
23(1)
Crossover operators for binary encoding
23(1)
Crossover operators for real-coded genetic algorithms
24(1)
Mutation operators
25(1)
Gaussian mutation
26(1)
Cauchy mutation
26(1)
Diversity mutation
26(1)
Levy flight mutation
27(1)
Power mutation
27(1)
Termination conditions
28(1)
Fitness limit
28(1)
Maximum number of generations
28(1)
Maximum stall time
28(1)
Maximum runtime
28(1)
Best fitness value
28(1)
Adaptive genetic algorithm
28(1)
Differential evolution
29(1)
Mutation
30(1)
Crossover
30(1)
Selection
30(1)
Chaotic differential evolution
31(1)
Differential evolution example
32(1)
Ackley function approximation
32(1)
References
33(4)
3 Swarm Intelligence and Particle Swarm Optimization
37(30)
Particle swarm optimization algorithm
37(2)
Hyper-parameters
39(1)
Acceleration coefficients
39(1)
Inertia weight
39(2)
Stopping criteria
41(1)
Maximum generation number
41(1)
Maximum stall time
41(1)
Maximum runtime
41(1)
Best fitness value
41(1)
Population convergence
41(1)
Fitness convergence
42(1)
Swarm topologies
42(1)
Global or fully connected
43(1)
Local or ring topology
43(1)
Von Neumann
44(1)
Star topology
44(1)
Mesh topology
44(1)
Random topology
44(1)
Tree or hierarchical topology
44(1)
Dynamic or adaptive topologies
44(1)
Boundary handling approaches
45(1)
Hyperbolic method
45(1)
Infinity or invisible wall
45(1)
Nearest or boundary or absorb
46(1)
Random
46(1)
Random-half
46(1)
Periodic
46(1)
Exponential
47(1)
Mutation
47(1)
Reflect methods
47(1)
Random damping
47(1)
PSO with mutation
47(1)
Gaussian mutation PSO
48(1)
Cauchy mutation PSO
48(1)
Michalewicz non-uniform mutation
49(1)
Chaotic PSO with Michalewicz mutation
49(1)
Random mutation PSO
50(1)
Constant mutation PSO
50(1)
Stagnant mutation
50(1)
Quantum PSO
50(1)
Delta well quantum PSO
51(1)
Harmonic quantum PSO
52(1)
Multi-objective PSO
53(2)
Geometric PSO
55(2)
PSO in neural network optimization
57(1)
PSO as weight optimizer
57(1)
PSO as topology optimizer
57(1)
Swarm optimization examples
58(1)
Sphere function
58(3)
Griewank function
61(1)
Rastrigin function
61(1)
Ackley function
62(1)
Schwefel function
63(1)
References
64(3)
4 Ant Colony Optimization and Artificial Bee Colony
67(20)
Ant colony optimization (ACO)
67(1)
Introduction
67(2)
Ant system (AS)
69(3)
Ant colony system (ACS)
72(1)
Rank-based ant system (RB-AS)
73(1)
Max-min ant system (MMAS)
74(1)
Population-based ACO
75(1)
Artificial bee colony (ABC)
76(1)
Bee colony foraging behavior
76(1)
ABC algorithm
77(3)
Selection methods
80(1)
Boundary handling approaches
81(1)
References
82(5)
5 Cuckoo Search and Bat Swarm Algorithm
87(24)
Cuckoo search
87(1)
Cuckoo breeding behavior and Levy flights
87(1)
Cuckoo search algorithm
88(3)
Cuckoo search variants
91(1)
Chaotic cuckoo search
91(3)
Discrete binary cuckoo search
94(1)
Hybrid self-adaptive cuckoo search
95(3)
Bat algorithm
98(1)
Bat algorithm inspiration
98(2)
Bat movement
100(1)
Bat algorithm variants
101(1)
Binary bat algorithm
101(1)
Chaotic bat algorithm
102(1)
1st Chaotic bat algorithm
102(1)
2nd Chaotic bat algorithm
103(1)
3rd Chaotic bat algorithm
103(1)
Self-adaptive bat algorithm
103(1)
Step-control mechanism
103(2)
Mutation mechanism
105(1)
Bat algorithm with double mutation
105(1)
Time factor modification
105(1)
Cauchy mutation operator modification
106(1)
Gaussian mutation operator
107(1)
References
107(4)
6 Firefly Algorithm, Harmony Search and Cat
111(20)
Swarm Algorithm
Firefly algorithm
111(3)
Firefly algorithm variants
114(1)
Firefly algorithm with Levy flights
114(2)
Chaotic firefly algorithms
116(1)
Harmony search algorithm
117(2)
Harmony search example
119(1)
Harmony search variants
120(1)
Improved harmony search algorithm
120(1)
Chaotic harmony search
121(2)
Cat swarm optimization
123(1)
Cat swarm algorithm
123(1)
Basic description of Cat Swarm Algorithm
124(1)
Cat algorithm variants
125(1)
Binary discrete Cat algorithm
125(1)
Improved cat swarm optimization
126(2)
References
128(3)
7 Grey Wolf, Whale and Grasshopper Optimization
131(26)
Grey wolf optimization
131(1)
Encircling prey
132(1)
Hunting
133(1)
Attacking prey (exploitation)
134(1)
Search for prey (exploration)
134(1)
Grey wolf algorithm variants
135(1)
Binary grey wolf optimization
135(4)
Grey wolf with Levy flight
139(2)
Whale optimization algorithm
141(1)
Encircling prey
141(1)
Bubble-net attacking strategy (exploitation phase)
142(3)
Whale optimization variants
145(1)
Whale optimization with Levy flight
145(2)
Binary whale optimization algorithm
147(1)
Grasshopper optimization algorithm
148(4)
Grasshopper optimization variants
152(1)
Chaotic grasshopper optimization algorithm
152(1)
Improved grasshopper optimization algorithm
153(1)
References
154(3)
8 Machine Learning Optimization Applications
157(22)
Artificial neural networks
157(1)
Weight optimization of a neural network
158(1)
Topology optimization of a neural network
159(1)
Neural network training with PSO, ACO, GA
159(1)
Experimental setup
159(1)
Genetic algorithm parameters
159(1)
PSO parameters
160(1)
ACO parameters
160(1)
Experimental results
160(1)
Feature selection with swarm intelligence and genetic algorithm
161(1)
Problem definition
161(1)
Data analysis in machine learning
161(1)
Energy consumption dataset
162(1)
Data Pre-processing
162(1)
Normalization
162(2)
Processing dataset outliers
164(1)
Cost-based feature selection with swarm intelligence
165(1)
Correlation-based feature selection with swarm intelligence
166(1)
Experimental setup
166(1)
Genetic algorithm
167(1)
GA algorithm parameters
167(1)
Genetic algorithm results
167(1)
Geometric PSO
168(1)
GPSO parameters
168(1)
GPSO results
168(1)
Chaotic harmony search
169(1)
Algorithm parameters
169(1)
Chaotic harmony search results
170(1)
Chaotic Cuckoo Search
171(1)
Algorithm parameters
171(1)
Chaotic Cuckoo Search results
171(1)
Evolutionary algorithm
172(1)
EA parameters
172(1)
EA results
173(1)
Predictions with reduced features, SVM and random forest
174(1)
Crime forecasting with PSO-SVM
175(2)
References
177(2)
9 Swarm and Evolutionary Intelligence in Deep Learning
179(15)
Deep LSTM and Bi-LSTM networks
179(2)
Deep CNN (Convolutional Neural Networks)
181(1)
CNN and LSTM optimization
182(1)
Topology optimization
182(1)
Weight optimization
183(1)
Experiments
183(1)
Bi-LSTM optimization
183(1)
Dataset
183(1)
Objective function
184(1)
Experimental setup
184(1)
Genetic algorithm parameters
184(1)
Adaptive w-PSO parameters
184(1)
Bidirectional LSTM training parameters
185(4)
CNN optimization
189(1)
CNN-PSO model
189(1)
Evaluation metrics
190(1)
Covid-19 chest X-ray dataset
191(1)
Experimental results
192(1)
CNN without PSO
192(1)
CNN optimized with PSO
193(1)
References 194(3)
Index 197
Georgios N. Kouziokas is a Lecturer at the University of Thessaly, Greece. He holds a Ph.D. in artificial intelligence in decision systems from the University of Thessaly. He holds four Masters of Science (MSc) in: computer science, applied mathematics, education, geographic information systems and environmental spatial analysis and a BSc in computer science.

He serves as an editor in two international journals about the application of artificial intelligence, editorial board member and associate editor in several international journals. He has reviewed for more than 60 international journals. He was awarded with the Emerging Scholar Award 2018 by the University of Illinois, USA for his Ph.D. achievements. Also, he was awarded with the Top Peer Reviewer Award 2018, 2019 by Publons organization, part of Web of Science.

He has more than 45 publications in peer-reviewed international scientific journals, book chapters and conference proceedings from major publishers, like Elsevier and Springer. He has served as a member of the organizing committee, program chair in several international conferences. His major research areas include work related to Artificial Intelligence, Computational Intelligence and Optimization, Swarm Intelligence, Machine Learning, Deep Learning, Neuro-Fuzzy Logic, Applied Mathematics, Information Systems, Educational Informatics, Environmental Informatics, Data Analysis, AI in Education, AI in Public Management, AI in justice, AI in Image Processing/Remote Sensing - Geographic Information Systems, Robotics, Quantum Artificial Intelligence and Cyber-Security.
Püsilink: https://www.kriso.ee/db/9781003247746_pe.html
Märksõnad: