Neural Network Algorithms and Their Engineering Applications presents the relevant techniques used to improve the global search ability of neural network algorithms in solving complex engineering problems with multimodal properties. The book provides readers with a complete study of how to use artificial neural networks to design a population-based metaheuristic algorithm, which in turn promotes the application of artificial neural networks in the field of engineering optimization.The authors provide a deep discussion for the potential application of machine learning methods in improving the optimization performance of the neural network algorithm, helping readers understand how to use machine learning methods to design improved versions of the algorithm. Users will find a wealth of source code that covers all applied algorithms. Code applications enhance readers' understanding of methods covered and facilitate readers' ability to apply the algorithms to their own research and development projects.
Computational Intelligence for Genomics Data presents an overview of machine learning and deep learning techniques being developed for the analysis of genomic data and the development of disease prediction models. The book focuses on machine and deep learning techniques applied to dimensionality reduction, feature extraction, and expressive gene selection. It includes designs, algorithms, and simulations on MATLAB and Python for larger prediction models and explores the possibilities of software and hardware-based applications and devices for genomic disease prediction. With the inclusion of important case studies and examples, this book will be a helpful resource for researchers, graduate students, and professional engineers.
Nature-Inspired Optimization Algorithms provides a systematic introduction to all major nature-inspired algorithms for optimization. The book's unified approach, balancing algorithm introduction, theoretical background and practical implementation, complements extensive literature with well-chosen case studies to illustrate how these algorithms work. Topics include particle swarm optimization, ant and bee algorithms, simulated annealing, cuckoo search, firefly algorithm, bat algorithm, flower algorithm, harmony search, algorithm analysis, constraint handling, hybrid methods, parameter tuning and control, as well as multi-objective optimization. This book can serve as an introductory book for graduates, doctoral students and lecturers in computer science, engineering and natural sciences. It can also serve a source of inspiration for new applications. Researchers and engineers as well as experienced experts will also find it a handy reference.
The Intelligent Systems Series publishes reference works and handbooks in three core sub-topic areas: Intelligent Automation, Intelligent Transportation Systems, and Intelligent Computing. They include theoretical studies, design methods, and real-world implementations and applications. The series' readership is broad, but focuses on engineering, electronics, and computer science. Budget constraints and optimization in sponsored search auctions takes into account consideration of the entire life cycle of campaigns for researchers and developers working on search systems and ROI maximization. The highly experienced authors compiled their knowledge and experience to provide insight, algorithms and development techniques for successful optimized/constrained systems. The book presents a cutting-edge budget optimization approach that embraces three-level budget decisions in the life cycle of search auctions: allocation across markets at the system level, distribution over temporal slots at the campaign level, and real-time adjustment at the keyword level.
Swarm Intelligence and bio-inspired computation have become increasing popular in the last two decades. Bio-inspired algorithms such as ant colony algorithms, bat algorithms, bee algorithms, firefly algorithms, cuckoo search and particle swarm optimization have been applied in almost every area of science and engineering with a dramatic increase of number of relevant publications. This book reviews the latest developments in swarm intelligence and bio-inspired computation from both the theory and application side, providing a complete resource that analyzes and discusses the latest and future trends in research directions. It can help new researchers to carry out timely research and inspire readers to develop new algorithms. With its impressive breadth and depth, this book will be useful for advanced undergraduate students, PhD students and lecturers in computer science, engineering and science as well as researchers and engineers.
Computational Intelligence: Concepts to Implementations provides the most complete and practical coverage of computational intelligence tools and techniques to date. This book integrates various natural and engineering disciplines to establish Computational Intelligence. This is the first comprehensive textbook on the subject, supported with lots of practical examples. It asserts that computational intelligence rests on a foundation of evolutionary computation. This refreshing view has set the book apart from other books on computational intelligence. This book lays emphasis on practical applications and computational tools, which are very useful and important for further development of the computational intelligence field. Focusing on evolutionary computation, neural networks, and fuzzy logic, the authors have constructed an approach to thinking about and working with computational intelligence that has, in their extensive experience, proved highly effective. The book moves clearly and efficiently from concepts and paradigms to algorithms and implementation techniques by focusing, in the early chapters, on the specific con. It explores a number of key themes, including self-organization, complex adaptive systems, and emergent computation. It details the metrics and analytical tools needed to assess the performance of computational intelligence tools. The book concludes with a series of case studies that illustrate a wide range of successful applications. This book will appeal to professional and academic researchers in computational intelligence applications, tool development, and systems.
Foundations of Genetic Algorithms, Volume 6 is the latest in a series of books that records the prestigious Foundations of Genetic Algorithms Workshops, sponsored and organised by the International Society of Genetic Algorithms specifically to address theoretical publications on genetic algorithms and classifier systems. Genetic algorithms are one of the more successful machine learning methods. Based on the metaphor of natural evolution, a genetic algorithm searches the available information in any given task and seeks the optimum solution by replacing weaker populations with stronger ones.
An essential capacity of intelligence is the ability to learn. An artificially intelligent system that could learn would not have to be programmed for every eventuality; it could adapt to its changing environment and conditions just as biological systems do. Illustrating Evolutionary Computation with Mathematica introduces evolutionary computation to the technically savvy reader who wishes to explore this fascinating and increasingly important field. Unique among books on evolutionary computation, the book also explores the application of evolution to developmental processes in nature, such as the growth processes in cells and plants. If you are a newcomer to the evolutionary computation field, an engineer, a programmer, or even a biologist wanting to learn how to model the evolution and coevolution of plants, this book will provide you with a visually rich and engaging account of this complex subject.
Problem solving is the very area of articifical intelligence AI which, probably, will never result in a complete set of formalized theories, in a pragmatic philosphy, or in a "universal" applied discipline. Studying questions concerning this area, encompasses different concepts, models and theories. This volume of the series looks at classifying problems, interpreting them, and the methods of solving them. The final chapter covers future concepts such as universal problem solving approach restoration, weak methods becoming strong, the role of formal logic in future developments, human factors and other paradigms.Different groups of readers such as mathematicians, specialists in computer sciences, and programmers will find this title of interest. Post-graduates and the students specializing in AI and applied mathematics will also find the work useful.