The objective of the series has always been to provide a forum in which leading contributors to an area can write about significant bodies of research in which they are involved. The operating procedure has been to invite contributions from interesting, active investigators, and then allow them essentially free rein to present their perspectives on important research problems. The result of such invitations over the past two decades has been collections of papers which consist of thoughtful integrations providing an overview of a particular scientific problem. The series has an excellent tradition of high quality papers and is widely read by researchers in cognitive and experimental psychology.

Handbook of Categorization in Cognitive Science, Second Edition presents the study of categories and the process of categorization as viewed through the lens of the founding disciplines of the cognitive sciences, and how the study of categorization has long been at the core of each of these disciplines. The literature on categorization reveals there is a plethora of definitions, theories, models and methods to apprehend this central object of study. The contributions in this handbook reflect this diversity. For example, the notion of category is not uniform across these contributions, and there are multiple definitions of the notion of concept. Furthermore, the study of category and categorization is approached differently within each discipline. For some authors, the categories themselves constitute the object of study, whereas for others, it is the process of categorization, and for others still, it is the technical manipulation of large chunks of information. Finally, yet another contrast has to do with the biological versus artificial nature of agents or categorizers. - Defines notions of category and categorization - Discusses the nature of categories: discrete, vague, or other - Explores the modality effects on categories - Bridges the category divide - calling attention to the bridges that have already been built, and avenues for further cross-fertilization between disciplines

Machine learning is the attempt to imitate human categorization of perceived reality in computers. It is driven by the desire to provide machines that are as open-minded, intelligent and flexible as humans. The central goal is to provide classifications for arbitrary types of input data: Labels that characterize the data correctly, given some examples. Machine learning has been a research topic of computer science for several decades. This book summarizes the major findings, explains the practically relevant methods and discusses their communalities and differences. In the first of three parts, we introduce the setting, goals and all necessary tools for the definition, application and evaluation of learning algorithms. The second part discusses and compares the various algorithms employed in machine categorization today. We structure them in four groups: the optimization algorithms, risk minimization approaches, those that employ probabilistic inference and those that imitate neural inference processes. Outstanding examples from the list of algorithms are the vector space mode, the support vector machine, Bayes and Markov processes, conditional random fields, radial basis function networks and methods employed for deep learning such as the Boltzmann machine. The third part reviews the algorithms and explores the theoretical frontiers of machine learning. In summary, we endeavor to provide a comprehensive yet intuitive introduction into the field of categorization. Neither parallels to human cognition are neglected nor recent developments in algorithm design or theoretical justification. As a research field, machine learning is gaining more and more attention. This book explains what it is, where it can be applied and how it is done.

The quest to create machines that can solve problems as humans do leads us to intelligent control. This field encompasses control systems that can adapt to changes and learn to improve their actions—traits typically associated with human intelligence. In this work we seek to determine how intelligent these classes of control systems are by quantifying their level of adaptability and learning. First we describe the stages of development towards intelligent control and present a definition based on literature. Based on the key elements of this definition, we propose a novel taxonomy of intelligent control methods, which assesses the extent to which they handle uncertainties in three areas: the environment, the controller, and the goals. This taxonomy is applicable to a variety of robotic and other autonomous systems, which we demonstrate through several examples of intelligent control methods and their classifications. Looking at the spread of classifications based on this taxonomy can help researchers identify where control systems can be made more intelligent.

Features information about a research program of the Cognitive Psychology Laboratory within the Cognitive Sciences Centre (CSC) of the Department of Psychology at the University of Southampton in Southampton, England. Explains that the program focuses on categorization capacity in humans and machines.

Note about this ebook: This ebook exploits many advanced capabilities with images, hypertext, and interactivity and is optimized for EPUB3-compliant book readers, especially Apple's iBooks and browser plugins. These features may not work on all ebook readers. We organize things. We organize information, information about things, and information about information. Organizing is a fundamental issue in many professional fields, but these fields have only limited agreement in how they approach problems of organizing and in what they seek as their solutions. The Discipline of Organizing synthesizes insights from library science, information science, computer science, cognitive science, systems analysis, business, and other disciplines to create an Organizing System for understanding organizing. This framework is robust and forward-looking, enabling effective sharing of insights and design patterns between disciplines that weren’t possible before. The Professional Edition includes new and revised content about the active resources of the "Internet of Things," and how the field of Information Architecture can be viewed as a subset of the discipline of organizing. You’ll find: 600 tagged endnotes that connect to one or more of the contributing disciplines Nearly 60 new pictures and illustrations Links to cross-references and external citations Interactive study guides to test on key points The Professional Edition is ideal for practitioners and as a primary or supplemental text for graduate courses on information organization, content and knowledge management, and digital collections. FOR INSTRUCTORS: Supplemental materials (lecture notes, assignments, exams, etc.) are available at http://disciplineoforganizing.org. FOR STUDENTS: Make sure this is the edition you want to buy. There's a newer one and maybe your instructor has adopted that one instead.

A Stochastic Grammar of Images is the first book to provide a foundational review and perspective of grammatical approaches to computer vision. In its quest for a stochastic and context sensitive grammar of images, it is intended to serve as a unified frame-work of representation, learning, and recognition for a large number of object categories. It starts out by addressing the historic trends in the area and overviewing the main concepts: such as the and-or graph, the parse graph, the dictionary and goes on to learning issues, semantic gaps between symbols and pixels, dataset for learning and algorithms. The proposal grammar presented integrates three prominent representations in the literature: stochastic grammars for composition, Markov (or graphical) models for contexts, and sparse coding with primitives (wavelets). It also combines the structure-based and appearance based methods in the vision literature. At the end of the review, three case studies are presented to illustrate the proposed grammar. A Stochastic Grammar of Images is an important contribution to the literature on structured statistical models in computer vision.

A revealing and surprising look at how classification systems can shape both worldviews and social interactions. What do a seventeenth-century mortality table (whose causes of death include "fainted in a bath," "frighted," and "itch"); the identification of South Africans during apartheid as European, Asian, colored, or black; and the separation of machine- from hand-washables have in common? All are examples of classification—the scaffolding of information infrastructures. In Sorting Things Out, Geoffrey C. Bowker and Susan Leigh Star explore the role of categories and standards in shaping the modern world. In a clear and lively style, they investigate a variety of classification systems, including the International Classification of Diseases, the Nursing Interventions Classification, race classification under apartheid in South Africa, and the classification of viruses and of tuberculosis. The authors emphasize the role of invisibility in the process by which classification orders human interaction. They examine how categories are made and kept invisible, and how people can change this invisibility when necessary. They also explore systems of classification as part of the built information environment. Much as an urban historian would review highway permits and zoning decisions to tell a city's story, the authors review archives of classification design to understand how decisions have been made. Sorting Things Out has a moral agenda, for each standard and category valorizes some point of view and silences another. Standards and classifications produce advantage or suffering. Jobs are made and lost; some regions benefit at the expense of others. How these choices are made and how we think about that process are at the moral and political core of this work. The book is an important empirical source for understanding the building of information infrastructures.

The ultimate goal of machines is to help humans to solve problems. Such problems range between two extremes: structured problems for which the solution is totally defined (and thus are easily programmed by humans), and random problems for which the solution is completely undefined (and thus cannot be programmed). Problems in the vast middle ground have solutions that cannot be well defined and are, thus, inherently hard to program. Machine Learning is the way to handle this vast middle ground, so that many tedious and difficult hand-coding tasks would be replaced by automatic learning methods. There are several machine learning tasks, and this work is focused on a major one, which is known as classification. Some classification problems are hard to solve, but we show that they can be decomposed into much simpler sub-problems. We also show that independently solving these sub-problems by taking into account their particular demands, often leads to improved classification performance.