Искусственный интеллект
Информатика и вычислительная техника
  • формат pdf
  • размер 3.4 МБ
  • добавлен 27 декабря 2011 г.
Butz M.V., Sigaud O., G?rard P. (eds.) Anticipatory Behavior in Adaptive Learning Systems. Foundations, Theories, and Systems
Издательство Springer, 2003, -309 pp.

The matter of anticipation is, as the editors of this volume state in their preface, a rather new topic. Given the almost constant use we make of anticipation in our daily living, it seems odd that the bulk of psychologists have persistently ignored it. However, the reason for this disregard is not difficult to find. The dogma of the scientific revolution had from the outset laid down the principle that future conditions and events could not influence the present. The law of causation clearly demands that causes should precede their effects and, therefore, concepts such as purpose, anticipation, and even intention were taboo because they were thought to involve things and happenings that lay ahead in time.
An analysis of the three concepts – purpose, anticipation, and intention – shows that they are rooted in the past and transcend the present only insofar as they contain mental representations of things to be striven for or avoided. Purposive or goal-directed action could be circumscribed as action carried out to attain something desirable. In each case, the particular action is chosen because, in the past, it has more or less reliably led to the desired end. The only way the future is involved in this procedure is through the belief that the experiential world manifests some regularity and allows the living organism to anticipate that what has worked in the past will continue to work in the future. This belief does not have to be conscious. Skinner’s rats continued to tu left in a maze where the left arm had been baited. They did so because the meat pellet they found the first time had reinforced them to repeat the tu to the left. But positive and negative reinforcement can work only with organisms that have evolved to act as though actions could be relied on to have constant results. The anticipation is implicit.
On the conceptual level, to anticipate means to project into what lies ahead a mental representation abstracted from past experience. In many cases we might not call such a projection an anticipation, although, in principle, it is. If, for instance, you are about to go for a walk, take a look at the sky, and pick up your umbrella, you do this because you have leaed from experience that the kind of clouds you saw through the window forebode rain. You are not anticipating an event but merely its possibility.
Tools are another example. The material and shape of a hammer have been developed and refined over the course of many generations’ experiences and you trust the tool you now hold in your hand to drive in future nails just as it drove in nails in the past. You may not actually anticipate its action, you simply believe that it will work.
If you have ever had the appalling driving experience of your foot going all the way to the floor board when you needed to brake, you will know just how unquestioningly you anticipated the brake pedal to do what it is supposed to do.
In one form or another anticipation pervades the fabric of our experience. As living organisms we constantly rely on a great deal of regularity in the world as we perceive it. It may not always work out, but apparently it works often enough for us to survive. To the examples I gave, many others could be added as illustration of the variety of the term’s applications. The contributions to this volume spring from very different sources and are likely to provide a welcome starting ground for the classification and modeling of different kinds of anticipation.

Introduction
Anticipatory Behavior: Exploiting Knowledge About the Future to Improve Current Behavior
Philosophical Considerations
Whose Anticipations?
Not Everything We Know We Leaed
From Cognitive Psychology to Cognitive Systems
Anticipatory Behavioral Control
Towards a Four Factor Theory of Anticipatory Leaing
Formulations, Distinctions, and Characteristics
Inteal Models and Anticipations in Adaptive Leaing Systems
Mathematical Foundations of Discrete and Functional Systems with Strong and Weak Anticipations
Anticipation Driven Artificial Personality: Building on Lewin and Loehlin
A Framework for Preventive State Anticipation
Symbols and Dynamics in Embodied Cognition: Revisiting a Robot Experiment
Systems, Evaluations, and Applications
Forward and Bidirectional Planning Based on Reinforcement Leaing and Neural Networks in a Simulated Robot
Sensory Anticipation for Autonomous Selection of Robot Landmarks
Representing Robot-Environment Interactions by Dynamical Features of Neuro-controllers
Anticipatory Guidance of Plot
Exploring the Value of Prediction in an Artificial Stock Market
Generalized State Values in an Anticipatory Leaing Classifier System
Похожие разделы
Смотрите также

Engelbrecht Andries P. Computational Intelligence: An Introduction

  • формат pdf
  • размер 4.06 МБ
  • добавлен 16 января 2011 г.
Second Edition. - John Wiley & Sons Ltd, 2007. - 630 p. Man has learned much from studies of natural systems, using what has been learned to develop new algorithmic models to solve complex problems. This book presents an introduction to some of these technological paradigms, under the umbrella of computational intelligence (CI). In this context, the book includes artificial neural networks, evolutionary computation, swarm intelligence, artifi...

Lungarella M., Iida F., Bongard J., Pfeifer R. 50 Years of Artificial Intelligence

  • формат djvu
  • размер 4.65 МБ
  • добавлен 17 ноября 2011 г.
Издательство Springer, 2007, -289 pp. Essays Dedicated to the 50th Anniversary ofArtificial Intelligence Half a century ago, at the now famous 1956 Dartmouth Conference, the fathers of Artificial Intelligence (AI) – among them John McCarthy, Marvin Minsky, Allen Newell, Claude Shannon, Herbert Simon, Oliver Selfridge, and Ray Solomonoff – convened under the premise that every aspect of learning or any other feature of intelligence can in princip...

Lytton W.W. From Computer to Brain: Foundations of Computational Neuroscience

  • формат pdf
  • размер 3.01 МБ
  • добавлен 24 августа 2011 г.
Springer, 2002. - 368 Pages. "In From Computer to Brain: Foundations of Computational Neuroscience, William W. Lytton provides a gentle but rigorous introduction to the art of modeling neurons and neural systems. It is an accessible entry to the methods and approaches used to model the brain at many different levels, ranging from synapses and dendrites to neurons and neural circuits. This book gives a balanced view of the wide range of modeling...

Mellouk A. (ed.) Advances in Reinforcement Learning

  • формат pdf
  • размер 12.29 МБ
  • добавлен 26 октября 2011 г.
Издательство InTech, 2011, -482 pp. Reinforcement Learning (RL) is oft en referred to as a branch of artificial intelligence and has been one of the central topics in a broad range of scientific fields for the last two decades. Understanding of RL is expected to provide a systematic understanding of adaptive behaviors, including simple classical and operant conditioning of animals as well as all complex social and economical human behaviors that...

Mellouk A., Chebira A. (eds.) Machine Learning

  • формат pdf
  • размер 8.06 МБ
  • добавлен 12 ноября 2011 г.
Издательство InTech, 2009, -430 pp. Machine Learning is often referred to as a branch of artificial intelligence which deals with the design and the development of algorithms and techniques that help machines to learn. Hence, it is closely related to various scientific domains as Optimization, Vision, Robotic and Control, Theoretical Computer Science, etc. Based on this, Machine Learning can be defined in various ways related to a scientific do...

Pearl J. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference

  • формат pdf
  • размер 20.8 МБ
  • добавлен 15 января 2011 г.
Morgan Kaufmann, 1988. - 552 pages. Probabilistic Reasoning in Intelligent Systems is a complete and accessible account of the theoretical foundations and computational methods that underlie plausible reasoning under uncertainty. The author provides a coherent explication of probability as a language for reasoning with partial belief and offers a unifying perspective on other AI approaches to uncertainty, such as the Dempster-Shafer formalism, t...

Pezzulo G., Butz M.V., Castelfranchi C., Falcone R. (eds.) The Challenge of Anticipation. A Unifying Framework for the Analysis and Design of Artificial Cognitive Systems

  • формат pdf
  • размер 3.42 МБ
  • добавлен 03 января 2012 г.
Издательство Springer, 2008, -294 pp. The general idea that brains anticipate the future, that they engage in prediction, and that one means of doing this is through some sort of inner model that can be run offline, has a long history. Some version of the idea was common to Aristotle, as well as to many medieval scholastics, to Leibniz and Hume, and in more recent times, to Kenneth Craik and Philip Johnson-Laird. One reason that this general ide...

Thielscher M. Action Programming Languages

  • формат pdf
  • размер 870.92 КБ
  • добавлен 25 января 2012 г.
Издательство Morgan & Claypool, 2008, -100 pp. Artificial systems that think and behave intelligently are one of the most exciting and challenging goals of Artificial Intelligence. Action Programming is the art and science of devising high-level control strategies for autonomous systems which employ a mental model of their environment and which reason about their actions as a means to achieve their goals. Applications of this programming par...

Wang C., Hill D.J. Deterministic Learning Theory for Identification, Recognition and Control

  • формат pdf
  • размер 10.94 МБ
  • добавлен 29 ноября 2011 г.
Издательство CRC Press, 2010, -218 pp. The problem of learning in dynamic environments is important and challenging. In the 1960s, learning from control of dynamical systems was studied extensively. At that time, learning was similar in meaning to other terms such as adaptation and self-organizing. Since the 1970s, learning theory has become a research discipline in the context of machine learning, and more recently as computational or statistic...

Zhang Y. (ed.) Machine Learning

  • формат pdf
  • размер 14.6 МБ
  • добавлен 12 ноября 2011 г.
Издательство InTech, 2010, -446 pp. The goal of this book is to present the key algorithms, theory and applications that from the core of machine learning. Learning is a fundamental activity. It is the process of constructing a model from complex world. And it is also the prerequisite for the performance of any new activity and, later, for the improvement in this performance. Machine learning is concerned with constructing computer programs tha...