In the 1990s, a new type of learning algorithm was developed, based on results from statistical learning theory: the Support Vector Machine (SVM). This gave rise to a new class of theoretically elegant learning machines that use a central concept of SVMs -- -kernels--for a number of learning tasks. Kernel machines provide a modular framework that can be adapted to different tasks and domains by…
These original essays summarize a decade of fruitful research and curriculum development using the LISP-derived language Logo. They discuss a range of issues in the areas of curriculum, learning, and mathematics, illustrating the ways in which Logo continues to provide a rich learning environment, one that allows pupil autonomy within challenging mathematical settings.Essays in the first sectio…
Linear classifiers in kernel spaces have emerged as a major topic within the field of machine learning. The kernel technique takes the linear classifier--a limited, but well-established and comprehensively studied model--and extends its applicability to a wide range of nonlinear pattern-recognition tasks such as natural language processing, machine vision, and biological sequence analysis. This…
"A Bradford book."It is the first detailed exploration of the problem of learning action strategies in the context of designing embedded systems that adapt their behavior to a complex, changing environment; such systems include mobile robots, factory process controllers, and long-term software databases.Learning to perform complex action strategies is an important problem in the fields of artif…
AnnotationOCLC-licensed vendor bibliographic record.
"A Bradford book."OCLC-licensed vendor bibliographic record.
This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible roles and to swi…
An accessible explanation of the hidden patterns found within the seemingly chaotic World Wide Web.Despite its haphazard growth, the Web hides powerful underlying regularities--from the organization of its links to the patterns found in its use by millions of users. Many of these regularities have been predicted on the basis of theoretical models based on a field of physics--statistical mechani…
Translated from the German."This classic 1936 work in vision science, written by a leading figure in Germany's Gestalt movement in psychology and appearing in English for the first time, addresses topics that remain of major interest to vision researchers today. Wolfgang Metzger's main argument, drawn from Gestalt theory, is that the objects we perceive in visual experience are not the objects …
"Charles Bazerman tells the story of the emergence of electric light as a story of symbols and communication. He examines how Edison and his colleagues represented light and power to themselves and to others as the technology was transformed from an idea to a daily fact of life. He looks at the rhetoric used to create meaning and value for the emergent technology in the laboratory, in patent of…