Papers presented at NIPS, the flagship meeting on neural computation, held in December 2004 in Vancouver.The annual Neural Information Processing Systems (NIPS) conference is the flagship meeting on neural computation. It draws a diverse group of attendees--physicists, neuroscientists, mathematicians, statisticians, and computer scientists. The presentations are interdisciplinary, with contributions in algorithms, learning theory, cognitive science, neuroscience, brain imaging, vision, speech and signal processing, reinforcement learning and control, emerging technologies, and applications. Only twenty-five percent of the papers submitted are accepted for presentation at NIPS, so the quality is exceptionally high. This volume contains the papers presented at the December, 2004 conference, held in Vancouver.

The annual Neural Information Processing Systems (NIPS) conference is the flagship meeting on neural computation and machine learning. This volume contains the papers presented at the December 2006 meeting, held in Vancouver.

Current robots and other artificial systems are typically able to accomplish only one single task. Overcoming this limitation requires the development of control architectures and learning algorithms that can support the acquisition and deployment of several different skills, which in turn seems to require a modular and hierarchical organization. In this way, different modules can acquire different skills without catastrophic interference, and higher-level components of the system can solve complex tasks by exploiting the skills encapsulated in the lower-level modules. While machine learning and robotics recognize the fundamental importance of the hierarchical organization of behavior for building robots that scale up to solve complex tasks, research in psychology and neuroscience shows increasing evidence that modularity and hierarchy are pivotal organization principles of behavior and of the brain. They might even lead to the cumulative acquisition of an ever-increasing number of skills, which seems to be a characteristic of mammals, and humans in particular. This book is a comprehensive overview of the state of the art on the modeling of the hierarchical organization of behavior in animals, and on its exploitation in robot controllers. The book perspective is highly interdisciplinary, featuring models belonging to all relevant areas, including machine learning, robotics, neural networks, and computational modeling in psychology and neuroscience. The book chapters review the authors' most recent contributions to the investigation of hierarchical behavior, and highlight the open questions and most promising research directions. As the contributing authors are among the pioneers carrying out fundamental work on this topic, the book covers the most important and topical issues in the field from a computationally informed, theoretically oriented perspective. The book will be of benefit to academic and industrial researchers and graduate students in related disciplines.

This book constitutes the refereed proceedings of the 11th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2009, held in Bordeaux, France in September/October 2009. The 43 revised full papers and 25 posters presented were carefully reviewed and selected from 115 submissions. The papers are organized in topical sections on technovision, fundamental mathematical techniques, image processing, coding and filtering, image and video analysis, computer vision, tracking, color, multispectral and special-purpose imaging, medical imaging, and biometrics.

This important text and reference for researchers and students in machine learning, game theory, statistics and information theory offers a comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction of individual sequences does not impose any probabilistic assumption on the data-generating mechanism. Yet, prediction algorithms can be constructed that work well for all possible sequences, in the sense that their performance is always nearly as good as the best forecasting strategy in a given reference class. The central theme is the model of prediction using expert advice, a general framework within which many related problems can be cast and discussed. Repeated game playing, adaptive data compression, sequential investment in the stock market, sequential pattern analysis, and several other problems are viewed as instances of the experts' framework and analyzed from a common nonstochastic standpoint that often reveals new and intriguing connections.

Discover the latest developments in multi-robot coordination techniques with this insightful and original resource Multi-Agent Coordination: A Reinforcement Learning Approach delivers a comprehensive, insightful, and unique treatment of the development of multi-robot coordination algorithms with minimal computational burden and reduced storage requirements when compared to traditional algorithms. The accomplished academics, engineers, and authors provide readers with both a high-level introduction to, and overview of, multi-robot coordination, and in-depth analyses of learning-based planning algorithms. You'll learn about how to accelerate the exploration of the team-goal and alternative approaches to speeding up the convergence of TMAQL by identifying the preferred joint action for the team. The authors also propose novel approaches to consensus Q-learning that address the equilibrium selection problem and a new way of evaluating the threshold value for uniting empires without imposing any significant computation overhead. Finally, the book concludes with an examination of the likely direction of future research in this rapidly developing field. Readers will discover cutting-edge techniques for multi-agent coordination, including: An introduction to multi-agent coordination by reinforcement learning and evolutionary algorithms, including topics like the Nash equilibrium and correlated equilibrium Improving convergence speed of multi-agent Q-learning for cooperative task planning Consensus Q-learning for multi-agent cooperative planning The efficient computing of correlated equilibrium for cooperative q-learning based multi-agent planning A modified imperialist competitive algorithm for multi-agent stick-carrying applications Perfect for academics, engineers, and professionals who regularly work with multi-agent learning algorithms, Multi-Agent Coordination: A Reinforcement Learning Approach also belongs on the bookshelves of anyone with an advanced interest in machine learning and artificial intelligence as it applies to the field of cooperative or competitive robotics.