By the mid-1980s researchers from artificial intelligence, computer science, brain and cognitive science, and psychology realized that the idea of computers as intelligent machines was inappropriate. The brain does not run "programs"; it does something entirely different. But what? Evolutionary theory says that the brain has evolved not to do mathematical proofs but to control our behavior, to ensure our survival. Researchers now agree that intelligence always manifests itself in behavior—thus it is behavior that we must understand. An exciting new field has grown around the study of behavior-based intelligence, also known as embodied cognitive science, "new AI," and "behavior-based AI."
This book provides a systematic introduction to this new way of thinking. After discussing concepts and approaches such as subsumption architecture, Braitenberg vehicles, evolutionary robotics, artificial life, self-organization, and learning, the authors derive a set of principles and a coherent framework for the study of naturally and artificially intelligent systems, or autonomous agents. This framework is based on a synthetic methodology whose goal is understanding by designing and building.
The book includes all the background material required to understand the principles underlying intelligence, as well as enough detailed information on intelligent robotics and simulated agents so readers can begin experiments and projects on their own. The reader is guided through a series of case studies that illustrate the design principles of embodied cognitive science.
Rolf Pfeifer is Professor of Computer Science and Director of the Artificial Intelligence Laboratory in the Department of Informatics at the University of Zurich. He is the author of Understanding Intelligence (MIT Press, 1999).
Christian Scheier is a Postdoctoral Fellow at the California Institute of Technology, Pasadena, California.
Under this perspective, what seems to be important is the ability to combine heterogeneous representation and problem-solving techniques. Research on heterogeneous, intelligent systems goes hand in hand with research on specific problem solving methods and paradigms, therefore representing their conceptual and practical glueing element. The papers contained in this proceedings are just one instance of such awareness activity in the international scientific community.
How could the body influence our thinking when it seems obvious that the brain controls the body? In How the Body Shapes the Way We Think, Rolf Pfeifer and Josh Bongard demonstrate that thought is not independent of the body but is tightly constrained, and at the same time enabled, by it. They argue that the kinds of thoughts we are capable of have their foundation in our embodiment—in our morphology and the material properties of our bodies.
This crucial notion of embodiment underlies fundamental changes in the field of artificial intelligence over the past two decades, and Pfeifer and Bongard use the basic methodology of artificial intelligence—"understanding by building"—to describe their insights. If we understand how to design and build intelligent systems, they reason, we will better understand intelligence in general. In accessible, nontechnical language, and using many examples, they introduce the basic concepts by building on recent developments in robotics, biology, neuroscience, and psychology to outline a possible theory of intelligence. They illustrate applications of such a theory in ubiquitous computing, business and management, and the psychology of human memory. Embodied intelligence, as described by Pfeifer and Bongard, has important implications for our understanding of both natural and artificial intelligence.
This classic book, first published in 1991, was one of the first to propose the “embodied cognition” approach in cognitive science. It pioneered the connections between phenomenology and science and between Buddhist practices and science—claims that have since become highly influential. Through this cross-fertilization of disparate fields of study, The Embodied Mind introduced a new form of cognitive science called “enaction,” in which both the environment and first person experience are aspects of embodiment. However, enactive embodiment is not the grasping of an independent, outside world by a brain, a mind, or a self; rather it is the bringing forth of an interdependent world in and through embodied action. Although enacted cognition lacks an absolute foundation, the book shows how that does not lead to either experiential or philosophical nihilism. Above all, the book's arguments were powered by the conviction that the sciences of mind must encompass lived human experience and the possibilities for transformation inherent in human experience.
This revised edition includes substantive introductions by Evan Thompson and Eleanor Rosch that clarify central arguments of the work and discuss and evaluate subsequent research that has expanded on the themes of the book, including the renewed theoretical and practical interest in Buddhism and mindfulness. A preface by Jon Kabat-Zinn, the originator of the mindfulness-based stress reduction program, contextualizes the book and describes its influence on his life and work.
Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data. This practical book shows you how.
By using concrete examples, minimal theory, and two production-ready Python frameworks—scikit-learn and TensorFlow—author Aurélien Géron helps you gain an intuitive understanding of the concepts and tools for building intelligent systems. You’ll learn a range of techniques, starting with simple linear regression and progressing to deep neural networks. With exercises in each chapter to help you apply what you’ve learned, all you need is programming experience to get started.Explore the machine learning landscape, particularly neural netsUse scikit-learn to track an example machine-learning project end-to-endExplore several training models, including support vector machines, decision trees, random forests, and ensemble methodsUse the TensorFlow library to build and train neural netsDive into neural net architectures, including convolutional nets, recurrent nets, and deep reinforcement learningLearn techniques for training and scaling deep neural netsApply practical code examples without acquiring excessive machine learning theory or algorithm details