Поиcк по сайту by Google


Rambler's Top100
Образование Крыму » Информатика. Компьютеры » Neural networks. Algorithms, applications, and programming techniques - Freeman J.A., Skapura D.M.

Neural networks. Algorithms, applications, and programming techniques - Freeman J.A., Skapura D.M.

Скачать
Название: Neural networks. Algorithms, applications, and programming techniques
Автор: Freeman J.A., Skapura D.M.
Категория: Информатика. Компьютеры
Тип: Книга
Дата: 23.02.2009 11:01:02
Скачано: 159
Оценка:
Описание: The appearance of digital computers and the development of modern theories of learning and neural processing both occurred at about the same time, during the late 1940s. Since that time, the digital computer has been used as a tool to model individual neurons as well as clusters of neurons, which are called neural networks. A large body of neurophysiological research has accumulated since then. For a good review of this research, see Neural and Brain Modeling by Ronald J. MacGregor [21]. The study of artificial neural systems (ANS) on computers remains an active field of biomedical research. Our interest in this text is not primarily neurological research. Rather, we wish to borrow concepts and ideas from the neuroscience field and to apply them to the solution of problems in other areas of science and engineering. The ANS models that are developed here may or may not have neurological relevance. Therefore, we have broadened the scope of the definition of ANS to include models that have been inspired by our current understanding of the brain, but that do not necessarily conform strictly to that understanding. The first examples of these new systems appeared in the late 1950s. The most common historical reference is to the work done by Frank Rosenblatt on a device called the perception. There are other examples, however, such as the development of the Adaline by Professor Bernard Widrow. Unfortunately, ANS technology has not always enjoyed the status in the fields of engineering or computer science that it has gained in the neuroscience community. Early pessimism concerning the limited capability of the perceptron effectively curtailed most research that might have paralleled the neurological research into ANS. From 1969 until the early 1980s, the field languished. The appearance, in 1969, of the book, Perceptions, by Marvin Minsky and Seymour Papert [26], is often credited with causing the demise of this technology. Whether this causal connection actually holds continues to be a subject for debate. Still, during those years, isolated pockets of research continued. Many of the network architectures discussed in this book were developed by researchers who remained active through the lean years. We owe the modern renaissance of neural-network technology to the successful efforts of those persistent workers. Today, we are witnessing substantial growth in funding for neural-network research and development. Conferences dedicated to neural networks and a
Файл: 4.17 МБ
Скачать