Computational Evolution Of Neural And Morphological Development

This book provides a basic yet unified overview of theory and methodologies for evolutionary developmental systems. Based on the author's extensive research into the synergies between various approaches to artificial intelligence including evolutionary computation, artificial neural networks, and systems biology, it also examines the inherent links between biological intelligence and artificial intelligence. The book begins with an introduction to computational algorithms used to understand and simulate biological evolution and development, including evolutionary algorithms, gene regulatory network models, multi-cellular models for neural and morphological development, and computational models of neural plasticity. Chap. 2 discusses important properties of biological gene regulatory systems, including network motifs, network connectivity, robustness and evolvability. Going a step further, Chap. 3 presents methods for synthesizing regulatory motifs from scratch and creating more complex regulatory dynamics by combining basic regulatory motifs using evolutionary algorithms. Multi-cellular growth models, which can be used to simulate either neural or morphological development, are presented in Chapters 4 and 5. Chap. 6 examines the synergies and coupling between neural and morphological evolution and development. In turn, Chap. 7 provides preliminary yet promising examples of how evolutionary developmental systems can help in self-organized pattern generation, referred to as morphogenetic self-organization, highlighting the great potentials of evolutionary developmental systems. Finally, Chap. 8 rounds out the book, stressing the importance and promise of the evolutionary developmental approach to artificial intelligence. Featuring a wealth of diagrams, graphs and charts to aid in comprehension, this book offers a valuable asset for graduate students, researchers and practitioners who are interested in pursuing a different approach to artificial intelligence.

This book provides a basic yet unified overview of theory and methodologies for evolutionary developmental systems. Based on the author’s extensive research into the synergies between various approaches to artificial intelligence including evolutionary computation, artificial neural networks, and systems biology, it also examines the inherent links between biological intelligence and artificial intelligence. The book begins with an introduction to computational algorithms used to understand and simulate biological evolution and development, including evolutionary algorithms, gene regulatory network models, multi-cellular models for neural and morphological development, and computational models of neural plasticity. Chap. 2 discusses important properties of biological gene regulatory systems, including network motifs, network connectivity, robustness and evolvability. Going a step further, Chap. 3 presents methods for synthesizing regulatory motifs from scratch and creating more complex regulatory dynamics by combining basic regulatory motifs using evolutionary algorithms. Multi-cellular growth models, which can be used to simulate either neural or morphological development, are presented in Chapters 4 and 5. Chap. 6 examines the synergies and coupling between neural and morphological evolution and development. In turn, Chap. 7 provides preliminary yet promising examples of how evolutionary developmental systems can help in self-organized pattern generation, referred to as morphogenetic self-organization, highlighting the great potentials of evolutionary developmental systems. Finally, Chap. 8 rounds out the book, stressing the importance and promise of the evolutionary developmental approach to artificial intelligence. Featuring a wealth of diagrams, graphs and charts to aid in comprehension, this book offers a valuable asset for graduate students, researchers and practitioners who are interested in pursuing a different approach to artificial intelligence.

Modularity—the attempt to understand systems as integrations of partially independent and interacting units—is today a dominant theme in the life sciences, cognitive science, and computer science. The concept goes back at least implicitly to the Scientific (or Copernican) Revolution, and can be found behind later theories of phrenology, physiology, and genetics; moreover, art, engineering, and mathematics rely on modular design principles. This collection broadens the scientific discussion of modularity by bringing together experts from a variety of disciplines, including artificial life, cognitive science, economics, evolutionary computation, developmental and evolutionary biology, linguistics, mathematics, morphology, paleontology, physics, theoretical chemistry, philosophy, and the arts. The contributors debate and compare the uses of modularity, discussing the different disciplinary contexts of "modular thinking" in general (including hierarchical organization, near-decomposability, quasi-independence, and recursion) or of more specialized concepts (including character complex, gene family, encapsulation, and mosaic evolution); what modules are, why and how they develop and evolve, and the implication for the research agenda in the disciplines involved; and how to bring about useful cross-disciplinary knowledge transfer on the topic. The book includes a foreword by the late Herbert A. Simon addressing the role of near-decomposability in understanding complex systems. Contributors: Lee Altenberg, Lauren W. Ancel-Meyers, Carl Anderson, Robert B. Brandon, Angela D. Buscalioni, Raffaele Calabretta, Werner Callebaut, Anne De Joan, Rafael Delgado-Buscalioni, Gunther J. Eble, Walter Fontana, Fernand Gobet, Alicia de la Iglesia, Slavik V. Jablan, Luigi Marengo, Daniel W. McShea, Jason Mezey, D. Kimbrough Oller, Domenico Parisi, Corrado Pasquali, Diego Rasskin-Gutman, Gerhard Schlosser, Herbert A. Simon, Roger D. K. Thomas, Marco Valente, Boris M. Velichkovsky, Gunter P. Wagner, Rasmus G. Winter Vienna Series in Theoretical Biology

The two volume set LNCS 5506 and LNCS 5507 constitutes the thoroughly refereed post-conference proceedings of the 15th International Conference on Neural Information Processing, ICONIP 2008, held in Auckland, New Zealand, in November 2008. The 260 revised full papers presented were carefully reviewed and selected from numerous ordinary paper submissions and 15 special organized sessions. 116 papers are published in the first volume and 112 in the second volume. The contributions deal with topics in the areas of data mining methods for cybersecurity, computational models and their applications to machine learning and pattern recognition, lifelong incremental learning for intelligent systems, application of intelligent methods in ecological informatics, pattern recognition from real-world information by svm and other sophisticated techniques, dynamics of neural networks, recent advances in brain-inspired technologies for robotics, neural information processing in cooperative multi-robot systems.

Conceived for both computer scientists and biologists alike, this collection of 22 essays highlights the important new role that computers play in developmental biology research. Essays show how through computer modeling, researchers gain further insight into developmental processes. Featured essays also cover their use in designing computer algorithms to tackle computer science problems in areas like neural network design, robot control, evolvable hardware, and more. Peter Bentley, noted for his prolific research on evolutionary computation, and Sanjeev Kumar head up a respected team to guide readers through these very complex and fascinating disciplines. * Covers both developmental biology and computational development -- the only book of its kind! * Provides introductory material and more detailed information on BOTH disciplines * Includes contribututions from Richard Dawkins, Lewis Wolpert, Ian Stewart, and many other experts

A comprehensive overview of an interdisciplinary approach to robotics that takes direct inspiration from the developmental and learning phenomena observed in children's cognitive development. Developmental robotics is a collaborative and interdisciplinary approach to robotics that is directly inspired by the developmental principles and mechanisms observed in children's cognitive development. It builds on the idea that the robot, using a set of intrinsic developmental principles regulating the real-time interaction of its body, brain, and environment, can autonomously acquire an increasingly complex set of sensorimotor and mental capabilities. This volume, drawing on insights from psychology, computer science, linguistics, neuroscience, and robotics, offers the first comprehensive overview of a rapidly growing field. After providing some essential background information on robotics and developmental psychology, the book looks in detail at how developmental robotics models and experiments have attempted to realize a range of behavioral and cognitive capabilities. The examples in these chapters were chosen because of their direct correspondence with specific issues in child psychology research; each chapter begins with a concise and accessible overview of relevant empirical and theoretical findings in developmental psychology. The chapters cover intrinsic motivation and curiosity; motor development, examining both manipulation and locomotion; perceptual development, including face recognition and perception of space; social learning, emphasizing such phenomena as joint attention and cooperation; language, from phonetic babbling to syntactic processing; and abstract knowledge, including models of number learning and reasoning strategies. Boxed text offers technical and methodological details for both psychology and robotics experiments.

One of the nation's leading neuroscientists presents a radically new view of the function of the brain and the nervous system. Its central idea is that the nervous system in each individual operates as a selective system resembling natural selection in evolution, but operating by different mechanisms. This far-ranging theory of brain functions is bound to stimulate renewed discussion of such philosophical issues as the mind-body problem, the origins of knowledge and the perceptual bases of language. Notes and Index.

Self-organizing approaches inspired from biological systems, such as social insects, genetic, molecular and cellular systems under morphogenesis, and human mental development, has enjoyed great success in advanced robotic systems that need to work in dynamic and changing environments. Compared with classical control methods for robotic systems, the major advantages of bio-inspired self-organizing robotic systems include robustness, self-repair and self-healing in the presence of system failures and/or malfunctions, high adaptability to environmental changes, and autonomous self-organization and self-reconfiguration without a centralized control. “Bio-inspired Self-organizing Robotic Systems” provides a valuable reference for scientists, practitioners and research students working on developing control algorithms for self-organizing engineered collective systems, such as swarm robotic systems, self-reconfigurable modular robots, smart material based robotic devices, unmanned aerial vehicles, and satellite constellations.