Kay Chen Tan

A remarkable facet of the human brain is its ability to manage multiple tasks with apparent simultaneity. Knowledge learned from one task can then be used to enhance problem-solving in other related tasks. In machine learning, the idea of leveraging relevant information across related tasks as inductive biases to enhance learning performance has attracted significant interest. In contrast, attempts to emulate the human brain’s ability to generalize in optimization – particularly in population-based evolutionary algorithms – have received little attention to date. Recently, a novel evolutionary search paradigm, Evolutionary Multi-Task (EMT) optimization, has been proposed in the realm of evolutionary computation. In contrast to traditional evolutionary searches, which solve a single task in a single run, evolutionary multi-tasking algorithm conducts searches concurrently on multiple search spaces corresponding to different tasks or optimization problems,each possessing a unique function landscape. By exploiting the latent synergies among distinct problems, the superior search performance of EMT optimization in terms of solution quality and convergence speed has been demonstrated in a variety of continuous, discrete, and hybrid (mixture of continuous and discrete) tasks. This book discusses the foundations and methodologies of developing evolutionary multi-tasking algorithms for complex optimization, including in domains characterized by factors such as multiple objectives of interest, high-dimensional search spaces and NP-hardness.

A remarkable facet of the human brain is its ability to manage multiple tasks with apparent simultaneity. Knowledge learned from one task can then be used to enhance problem-solving in other related tasks. In machine learning, the idea of leveraging relevant information across related tasks as inductive biases to enhance learning performance has attracted significant interest. In contrast, attempts to emulate the human brain’s ability to generalize in optimization – particularly in population-based evolutionary algorithms – have received little attention to date. Recently, a novel evolutionary search paradigm, Evolutionary Multi-Task (EMT) optimization, has been proposed in the realm of evolutionary computation. In contrast to traditional evolutionary searches, which solve a single task in a single run, evolutionary multi-tasking algorithm conducts searches concurrently on multiple search spaces corresponding to different tasks or optimization problems,each possessing a unique function landscape. By exploiting the latent synergies among distinct problems, the superior search performance of EMT optimization in terms of solution quality and convergence speed has been demonstrated in a variety of continuous, discrete, and hybrid (mixture of continuous and discrete) tasks. This book discusses the foundations and methodologies of developing evolutionary multi-tasking algorithms for complex optimization, including in domains characterized by factors such as multiple objectives of interest, high-dimensional search spaces and NP-hardness.

This book introduces the linkage between evolutionary computation and complex networks and the advantages of cross-fertilising ideas from both fields. Instead of introducing each field individually, the authors focus on the research that sits at the interface of both fields. The book is structured to address two questions: (1) how complex networks are used to analyze and improve the performance of evolutionary computation methods? (2) how evolutionary computation methods are used to solve problems in complex networks? The authors interweave complex networks and evolutionary computing, using evolutionary computation to discover community structure, while also using network analysis techniques to analyze the performance of evolutionary algorithms. The book is suitable for both beginners and senior researchers in the fields of evolutionary computation and complex networks.

This book introduces the linkage between evolutionary computation and complex networks and the advantages of cross-fertilising ideas from both fields. Instead of introducing each field individually, the authors focus on the research that sits at the interface of both fields. The book is structured to address two questions: (1) how complex networks are used to analyze and improve the performance of evolutionary computation methods? (2) how evolutionary computation methods are used to solve problems in complex networks? The authors interweave complex networks and evolutionary computing, using evolutionary computation to discover community structure, while also using network analysis techniques to analyze the performance of evolutionary algorithms. The book is suitable for both beginners and senior researchers in the fields of evolutionary computation and complex networks.

Neural Networks: Computational Models and Applications covers a wealth of important theoretical and practical issues in neural networks, including the learning algorithms of feed-forward neural networks, various dynamical properties of recurrent neural networks, winner-take-all networks and their applications in broad manifolds of computational intelligence: pattern recognition, uniform approximation, constrained optimization, NP-hard problems, and image segmentation. By presenting various computational models, this book is developed to provide readers with a quick but insightful understanding of the broad and rapidly growing areas in the neural networks domain. Besides laying down fundamentals on artificial neural networks, this book also studies biologically inspired neural networks. Some typical computational models are discussed, and subsequently applied to objection recognition, scene analysis and associative memory. The studies of bio-inspired models have important implications in computer vision and robotic navigation, as well as new efficient algorithms for image analysis. Another significant feature of the book is that it begins with fundamental dynamical problems in presenting the mathematical techniques extensively used in analyzing neurodynamics, thus allowing non-mathematicians to develop and apply these analytical techniques easily. Written for a wide readership, engineers, computer scientists and mathematicians interested in machine learning, data mining and neural networks modeling will find this book of value. This book will also act as a helpful reference for graduate students studying neural networks and complex dynamical systems.

Evolutionary algorithms are sophisticated search methods that have been found to be very efficient and effective in solving complex real-world multi-objective problems where conventional optimization tools fail to work well. Despite the tremendous amount of work done in the development of these algorithms in the past decade, many researchers assume that the optimization problems are deterministic and uncertainties are rarely examined. The primary motivation of this book is to provide a comprehensive introduction on the design and application of evolutionary algorithms for multi-objective optimization in the presence of uncertainties. In this book, we hope to expose the readers to a range of optimization issues and concepts, and to encourage a greater degree of appreciation of evolutionary computation techniques and the exploration of new ideas that can better handle uncertainties. "Evolutionary Multi-Objective Optimization in Uncertain Environments: Issues and Algorithms" is intended for a wide readership and will be a valuable reference for engineers, researchers, senior undergraduates and graduate students who are interested in the areas of evolutionary multi-objective optimization and uncertainties.

Multiobjective Evolutionary Algorithms and Applications provides comprehensive treatment on the design of multiobjective evolutionary algorithms and their applications in domains covering areas such as control and scheduling. Emphasizing both the theoretical developments and the practical implementation of multiobjective evolutionary algorithms, a profound mathematical knowledge is not required. Written for a wide readership, engineers, researchers, senior undergraduates and graduate students interested in the field of evolutionary algorithms and multiobjective optimization with some basic knowledge of evolutionary computation will find this book a useful addition to their book case.

Evolutionary algorithms are sophisticated search methods that have been found to be very efficient and effective in solving complex real-world multi-objective problems where conventional optimization tools fail to work well. Despite the tremendous amount of work done in the development of these algorithms in the past decade, many researchers assume that the optimization problems are deterministic and uncertainties are rarely examined. The primary motivation of this book is to provide a comprehensive introduction on the design and application of evolutionary algorithms for multi-objective optimization in the presence of uncertainties. In this book, we hope to expose the readers to a range of optimization issues and concepts, and to encourage a greater degree of appreciation of evolutionary computation techniques and the exploration of new ideas that can better handle uncertainties. "Evolutionary Multi-Objective Optimization in Uncertain Environments: Issues and Algorithms" is intended for a wide readership and will be a valuable reference for engineers, researchers, senior undergraduates and graduate students who are interested in the areas of evolutionary multi-objective optimization and uncertainties.

Neural Networks: Computational Models and Applications covers a wealth of important theoretical and practical issues in neural networks, including the learning algorithms of feed-forward neural networks, various dynamical properties of recurrent neural networks, winner-take-all networks and their applications in broad manifolds of computational intelligence: pattern recognition, uniform approximation, constrained optimization, NP-hard problems, and image segmentation. By presenting various computational models, this book is developed to provide readers with a quick but insightful understanding of the broad and rapidly growing areas in the neural networks domain. Besides laying down fundamentals on artificial neural networks, this book also studies biologically inspired neural networks. Some typical computational models are discussed, and subsequently applied to objection recognition, scene analysis and associative memory. The studies of bio-inspired models have important implications in computer vision and robotic navigation, as well as new efficient algorithms for image analysis. Another significant feature of the book is that it begins with fundamental dynamical problems in presenting the mathematical techniques extensively used in analyzing neurodynamics, thus allowing non-mathematicians to develop and apply these analytical techniques easily. Written for a wide readership, engineers, computer scientists and mathematicians interested in machine learning, data mining and neural networks modeling will find this book of value. This book will also act as a helpful reference for graduate students studying neural networks and complex dynamical systems.

This invaluable book comprehensively describes evolutionary robotics and computational intelligence, and how different computational intelligence techniques are applied to robotic system design. It embraces the most widely used evolutionary approaches with their merits and drawbacks, presents some related experiments for robotic behavior evolution and the results achieved, and shows promising future research directions. Clarity of explanation is emphasized such that a modest knowledge of basic evolutionary computation, digital circuits and engineering design will suffice for a thorough understanding of the material.The book is ideally suited to computer scientists, practitioners and researchers keen on computational intelligence techniques, especially the evolutionary algorithms in autonomous robotics at both the hardware and software levels.

This invaluable book comprehensively describes evolutionary robotics and computational intelligence, and how different computational intelligence techniques are applied to robotic system design. It embraces the most widely used evolutionary approaches with their merits and drawbacks, presents some related experiments for robotic behavior evolution and the results achieved, and shows promising future research directions. Clarity of explanation is emphasized such that a modest knowledge of basic evolutionary computation, digital circuits and engineering design will suffice for a thorough understanding of the material.The book is ideally suited to computer scientists, practitioners and researchers keen on computational intelligence techniques, especially the evolutionary algorithms in autonomous robotics at both the hardware and software levels.

The main subjects in this book relate to software development using cutting-edge technologies for real-world industrial automation applicationsA hands-on approach to applying a wide variety of emerging technologies to modern industrial practice problemsExplains key concepts through clear examples, ranging from simple to more complex problem domains, and all based on real-world industrial problemsA useful reference book for practicing engineers as well as an updated resource book for researchers

Multiobjective Evolutionary Algorithms and Applications provides comprehensive treatment on the design of multiobjective evolutionary algorithms and their applications in domains covering areas such as control and scheduling. Emphasizing both the theoretical developments and the practical implementation of multiobjective evolutionary algorithms, a profound mathematical knowledge is not required. Written for a wide readership, engineers, researchers, senior undergraduates and graduate students interested in the field of evolutionary algorithms and multiobjective optimization with some basic knowledge of evolutionary computation will find this book a useful addition to their book case.