Static and Dynamic Neural Networks: From Fundamentals to Advanced TheoryJohn Wiley & Sons, 5 апр. 2004 г. - Всего страниц: 752 Neuronale Netze haben sich in vielen Bereichen der Informatik und künstlichen Intelligenz, der Robotik, Prozeßsteuerung und Entscheidungsfindung bewährt. Um solche Netze für immer komplexere Aufgaben entwickeln zu können, benötigen Sie solide Kenntnisse der Theorie statischer und dynamischer neuronaler Netze. Aneignen können Sie sie sich mit diesem Lehrbuch! Alle theoretischen Konzepte sind in anschaulicher Weise mit praktischen Anwendungen verknüpft. Am Ende jedes Kapitels können Sie Ihren Wissensstand anhand von Übungsaufgaben überprüfen. |
Содержание
STATIC NEURAL NETWORKS | 103 |
DYNAMIC NEURAL NETWORKS | 295 |
SOME ADVANCED TOPICS IN NEURAL NETWORKS | 507 |
References and Bibliography | 687 |
Current Bibliographic Sources on Neural Networks | 711 |
Index | 715 |
Другие издания - Просмотреть все
Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory Madan Gupta,Liang Jin,Noriyasu Homma Недоступно для просмотра - 2003 |
Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory Madan Gupta,Liang Jin,Noriyasu Homma Недоступно для просмотра - 2004 |
Часто встречающиеся слова и выражения
activation function adaptive backpropagation binary neural network binary pattern biological Block diagram BP algorithm chapter cognitive computing convergence defined diagonal discussed dx(t dynamic neural network dynamic neural unit eigenvalues elements energy function equation equilibrium points error function Example feedforward neural networks Figure fundamental memories fuzzy logic fuzzy sets fuzzy system Gaussian given in Eqn globally asymptotically stable gradient Hamming distance hidden layers Hopfield dynamic neural Hopfield neural network initial input-output learning rate learning rule linear Lyapunov function mathematical MFNN network structure neural inputs neural models neural system neuron nonlinear mapping obtained operation output layer parameters partial derivatives pattern vectors problem radial basis function second-order shown in Fig sigmoidal function stable equilibrium points Stone-Weierstrass theorem symmetric synaptic weights synchronous system in Eqn threshold two-layered universal approximation updating weight matrix weight vector xp(k
Популярные отрывки
Стр. 580 - When an axon of cell A is near enough to excite a cell B and repeatedly or persistently takes part in firing it, some growth process or metabolic change takes place in one or both cells such that A's efficiency, as one of the cells firing B, is increased.
Стр. 16 - Today's computers, however, are merely being used for the storage and processing of numerical data (hard uncertainty and hard information). Should we not re-examine the functions of these computing tools in view of the increasing interests in subjects such as knowledgebased systems, expert systems and intelligent robotic systems and for solving problems related to decision and control? Human mentation acts upon cognitive information and the cognitive information is characterized by using relative...
Стр. 16 - ... was restricted only to a class of information arising from physical systems. If we want to emulate some of the cognitive functions (learning, remembering, reasoning, intelligence...
Стр. 43 - Models of neural networks described in the existing literature often consider the behavior of a single neuron as the basic computing unit for describing neural information processing operations. Each computing unit in the network is based on the concept of an idealized neuron. An ideal neuron is assumed to respond optimally to the applied inputs. However, experimental studies in neurophysiology show that the...
Стр. 16 - ... develop new mathematical tools and hardware. These new mathematical tools and hardware must deal with the simulation and processing of cognitive information and soft logic. Many new notions, although still...
Стр. 689 - Absolute stability of global pattern formation and parallel memory storage by competitive neural networks", IEEE Trans.
Стр. 705 - The pi-sigma network : an Efficient Higher-Order Neural Network for pattern classification and function approximation,
Стр. 7 - In neuronal information processing there are a variety of complex mathematical operations and mapping functions involved which synergically act in a parallel-cascade structure forming a complex pattern of neuronal layers evolving into a sort of pyramidical pattern.
Стр. 641 - Q, i=l,2,...,N (2.1) where x; (j=l,2,...,n) are the input variables to the fuzzy system, y is the output variable of the fuzzy system, and the fuzzy sets Ay in U; and C; are linguistic terms characterized by fuzzy membership functions AJJ(XJ) and Cj(y), respectively.
Стр. 7 - The biological neurons, over one hundred billion, in the central nervous systems (CNS) of humans play a very important role in various complex sensory, control and cognitive aspects of information processing and decision making [3-5].