Psychology is now ready for unified theories of cognition--so says Allen Newell, a leading investigator in computer science and cognitive psychology. Not everyone will agree on a single set of mechanisms that will explain the full range of human cognition, but such theories are within reach and we should strive to articulate them. In this book, Newell makes the case for unified theories by setting forth a candidate. After reviewing the foundational concepts of cognitive science--knowledge, representation, computation, symbols, architecture, intelligence, and search--Newell introduces Soar, an architecture for general cognition. A pioneer system in artificial intelligence, Soar is the first problem solver to create its own subgoals and learn continuously from its own experience. Newell shows how Soar's ability to operate within the real-time constraints of intelligent behavior, such as immediate-response and item-recognition tasks, illustrates important characteristics of the human cognitive structure. Throughout, Soar remains an exemplar: we know only enough to work toward a fully developed theory of cognition, but Soar's success so far establishes the viability of the enterprise. Given its integrative approach, Unified Theories of Cognition will be of tremendous interest to researchers in a variety of fields, including cognitive science, artificial intelligence, psychology, and computer science. This exploration of the nature of mind, one of the great problems of philosophy, should also transcend disciplines and attract a large scientific audience.

The six contributions in Connectionist Symbol Processing address the current tension within the artificial intelligence community between advocates of powerful symbolic representations that lack efficient learning procedures and advocates of relatively simple learning procedures that lack the ability to represent complex structures effectively. The authors seek to extend the representational power of connectionist networks without abandoning the automatic learning that makes these networks interesting.Aware of the huge gap that needs to be bridged, the authors intend their contributions to be viewed as exploratory steps in the direction of greater representational power for neural networks. If successful, this research could make it possible to combine robust general purpose learning procedures and inherent representations of artificial intelligence -- a synthesis that could lead to new insights into both representation and learning.

Recent work in cognitive science, much of it placed in opposition to a computational view of the mind, has argued that the concept of representation and theories based on that concept are not sufficient to explain the details of cognitive processing. These attacks on representation have focused on the importance of context sensitivity in cognitive processing, on the range of individual differences in performance, and on the relationship between minds and the bodies and environments in which they exist. In each case, models based on traditional assumptions about representation have been assumed to be too rigid to account for the effects of these factors on cognitive processing. In place of a representational view of mind, other formalisms and methodologies, such as nonlinear differential equations (or dynamical systems) and situated robotics, have been proposed as better explanatory tools for understanding cognition. This book is based on the notion that, while new tools and approaches for understanding cognition are valuable, representational approaches do not need to be abandoned in the course of constructing new models and explanations. Rather, models that incorporate representation are quite compatible with the kinds of complex situations being modeled with the new methods. This volume illustrates the power of this explicitly representational approach--labeled "cognitive dynamics"--in original essays by prominent researchers in cognitive science. Each chapter explores some aspect of the dynamics of cognitive processing while still retaining representations as the centerpiece of the explanations of the key phenomena. These chapters serve as an existence proof that representation is not incompatible with the dynamics of cognitive processing. The book is divided into sections on foundational issues about the use of representation in cognitive science, the dynamics of low level cognitive processes (such as visual and auditory perception and simple lexical priming), and the dynamics of higher cognitive processes (including categorization, analogy, and decision making).

This is a self-contained and systematic account of affine differential geometry from a contemporary view, not only covering the classical theory, but also introducing more modern developments. In order both to cover as much as possible and to keep the text of a reasonable size, the authors have concentrated on the significant features of the subject and their relationship and application to such areas as Riemannian, Euclidean, Lorentzian and projective differential geometry. In so doing, they also provide a modern introduction to the last. Some of the important geometric surfaces considered are illustrated by computer graphics, making this a physically and mathematically attractive book for all researchers in differential geometry, and for mathematical physicists seeking a quick entry to the subject.

Pattern Theory: From Representation to Inference provides a comprehensive and accessible overview of the modern challenges in signal, data and pattern analysis in speech recognition, computational linguistics, image analysis and computer vision. Aimed at graduate students in biomedical engineering, mathematics, computer science and electrical engineering with a good background in mathematics and probability, the text includes numerous exercises and an extensive bibliography. Additional resources including extended proofs, selected solutions and examples are available on a companion website. The book commences with a short overview of pattern theory and the basics of statistics and estimation theory. Chapters 3-6 discuss the role of representation of patterns via conditioning structure and Chapters 7 and 8 examine the second central component of pattern theory: groups of geometric transformation applied to the representation of geometric objects. Chapter 9 moves into probabilistic structures in the continuum, studying random processes and random fields indexed over subsets of Rn, and Chapters 10, 11 continue with transformations and patterns indexed over the continuum.Chapters 12-14 extend from the pure representations of shapes to the Bayes estimation of shapes and their parametric representation. Chapters 15 and 16 study the estimation of infinite dimensional shape in the newly emergent field of Computational Anatomy, and finally Chapters 17 and 18 look at inference, exploring random sampling approaches for estimation of model order and parametric representing of shapes.

In this groundbreaking work, computer scientist Leslie G. Valiant details a promising new computational approach to studying the intricate workings of the human brain. Focusing on the brain's enigmatic ability to access quickly a massive store of accumulated information during reasoning processes, the author asks how such feats are possible given the extreme constraints imposed by the brain's finite number of neurons, their limited speed of communication, and their restricted interconnectivity. Valiant proposes a "neuroidal model" that serves as a vehicle to explore these fascinating questions. While embracing the now classical theories of McCulloch and Pitts, the neuroidal model also accommodates state information in the neurons, more flexible timing mechanisms, a variety of assumptions about interconnectivity, and the possibility that different areas perform different functions. Programmable so that a wide range of algorithmic theories can be described and evaluated, the model provides a concrete computational language and a unified framework in which diverse cognitive phenomena--such as memory, learning, and reasoning--can be systematically and concurrently analyzed. Requiring no specialized knowledge, Circuits of the Mind masterfully offers an exciting new approach to brain science for students and researchers in computer science, neurobiology, neuroscience, artificial intelligence, and cognitive science.

This book is an introduction to pattern theory, the theory behind the task of analyzing types of signals that the real world presents to us. It deals with generating mathematical models of the patterns in those signals and algorithms for analyzing the data based on these models. It exemplifies the view of applied mathematics as starting with a collection of problems from some area of science and then seeking the appropriate mathematics for clarifying the experimental data and the underlying processes of producing these data. An emphasis is placed on finding the mathematical and, where needed, computational tools needed to reach those goals, actively involving the reader in this process. Among other examples and problems, the following areas are treated: music as a realvalued function of continuous time, character recognition, the decomposition of an image into regions with distinct colors and textures, facial recognition, and scaling effects present in natural images caused by their statistical selfsimilarity.

500個與「人」有關的漢字＋超過5,000個甲骨文、金文、篆文
收納在2張漢字樹狀圖！
一個台大電機系畢業、專精於電腦的「理工人」，在偶然的機會接觸了被認為許多從事文學創作研究的作家、專家也視為畏途的「文字學」，產生了濃厚的興趣；順著歷來各家的研究，進入了漢字構型的世界，流連忘返。隨著心得漸增，心頭的不解疑團也越來越多。
於是，他引入電腦強大的彙編整理能力，有系統地梳理漢字的構件，試圖找出解釋力更強的說法，在這個過程中，也越加感受到部首的限制與誤導。
部首是一個字組成的構件之一，因為有許多字都有，因而成為漢字分類的標記。但是，屬於同一個部首的字，彼此之間卻未必有關連。反之，有些看似不同的字，從漢字的演化發展來看，卻是關係密切。
作者長年浸淫在文字學的天地，尋索字與字之間的邏輯關連，濃縮在書中的「漢字樹狀圖」中。再透過作者清晰簡要的說明，即使對於在文字學毫無根基的讀者，也可以憑著自身對中文母語的使用經驗，得到許多新奇的發現與樂趣。

This systematic investigation of computation and mental phenomena by a noted psychologist and computer scientist argues that cognition is a form of computation, that the semantic contents of mental states are encoded in the same general way as computer representations are encoded. It is a rich and sustained investigation of the assumptions underlying the directions cognitive science research is taking.

Since its publication in 1949, D.O. Hebb's, The Organization of Behavior has been one of the most influential books in the fields of psychology and neuroscience. However, the original edition has been unavailable since 1966, ensuring that Hebb's comment that a classic normally means "cited but not read" is true in his case. This new edition rectifies a long-standing problem for behavioral neuroscientists--the inability to obtain one of the most cited publications in the field.
The Organization of Behavior played a significant part in stimulating the investigation of the neural foundations of behavior and continues to be inspiring because it provides a general framework for relating behavior to synaptic organization through the dynamics of neural networks.
D.O. Hebb was also the first to examine the mechanisms by which environment and experience can influence brain structure and function, and his ideas formed the basis for work on enriched environments as stimulants for behavioral development.
References to Hebb, the Hebbian cell assembly, the Hebb synapse, and the Hebb rule increase each year. These forceful ideas of 1949 are now applied in engineering, robotics, and computer science, as well as neurophysiology, neuroscience, and psychology--a tribute to Hebb's foresight in developing a foundational neuropsychological theory of the organization of behavior.

In bringing together seminal articles on the foundations of research, the first volume of Neurocomputing has become an established guide to the background of concepts employed in this burgeoning field. Neurocomputing 2 collects forty-one articles covering network architecture, neurobiological computation, statistics and pattern classification, and problems and applications that suggest important directions for the evolution of neurocomputing.James A. Anderson is Professor in the Department of Cognitive and Linguistic Sciences at Brown University. Andras Pellionisz is a Research Associate Professor in the Department of Physiology and Biophysics at New York Medical Center and a Senior National Research Council Associate to NASA. Edward Rosenfeld is editor and publisher of the newsletters Intelligence and Medical Intelligence.

Researchers will find Neurocomputing an essential guide to the concepts employed in this field that have been taken from disciplines as varied as neuroscience, psychology, cognitive science, engineering, and physics. A number of these important historical papers contain ideas that have not yet been fully exploited, while the more recent articles define the current direction of neurocomputing and point to future research. Each article has an introduction that places it in historical and intellectual perspective.
Included among the 43 articles are the pioneering contributions of McCulloch and Pitts, Hebb, and Lashley; innovative work by Von Neumann, Minsky and Papert, Cooper, Grossberg, and Kohonen; exciting new developments in parallel distributed processing.

Man has within a single generation found himself sharing the world with a strange new species: the computers and computer-like machines. Neither history, nor philosophy, nor common sense will tell us how these machines will affect us, for they do not do "work" as did machines of the Industrial Revolution. Instead of dealing with materials or energy, we are told that they handle "control" and "information" and even "intellectual processes." There are very few individuals today who doubt that the computer and its relatives are developing rapidly in capability and complexity, and that these machines are destined to play important (though not as yet fully understood) roles in society's future. Though only some of us deal directly with computers, all of us are falling under the shadow of their ever-growing sphere of influence, and thus we all need to understand their capabilities and their limitations. It would indeed be reassuring to have a book that categorically and systematically described what all these machines can do and what they cannot do, giving sound theoretical or practical grounds for each judgment. However, although some books have purported to do this, it cannot be done for the following reasons: a) Computer-like devices are utterly unlike anything which science has ever considered---we still lack the tools necessary to fully analyze, synthesize, or even think about them; and b) The methods discovered so far are effective in certain areas, but are developing much too rapidly to allow a useful interpretation and interpolation of results. The abstract theory---as described in this book---tells us in no uncertain terms that the machines' potential range is enormous, and that its theoretical limitations are of the subtlest and most elusive sort. There is no reason to suppose machines have any limitations not shared by man.