Results 1 - 10 of 6,886

Regularization networks and support vector machines

by Theodoros Evgeniou, Massimiliano Pontil, Tomaso Poggio - Advances in Computational Mathematics , 2000
"... Regularization Networks and Support Vector Machines are techniques for solving certain problems of learning from examples – in particular the regression problem of approximating a multivariate function from sparse data. Radial Basis Functions, for example, are a special case of both regularization a ..."
Abstract - Cited by 366 (38 self) - Add to MetaCart
Regularization Networks and Support Vector Machines are techniques for solving certain problems of learning from examples – in particular the regression problem of approximating a multivariate function from sparse data. Radial Basis Functions, for example, are a special case of both regularization

Regularization Theory and Neural Networks Architectures

by Federico Girosi, Michael Jones, Tomaso Poggio - Neural Computation , 1995
"... We had previously shown that regularization principles lead to approximation schemes which are equivalent to networks with one layer of hidden units, called Regularization Networks. In particular, standard smoothness functionals lead to a subclass of regularization networks, the well known Radial Ba ..."
Abstract - Cited by 395 (32 self) - Add to MetaCart
We had previously shown that regularization principles lead to approximation schemes which are equivalent to networks with one layer of hidden units, called Regularization Networks. In particular, standard smoothness functionals lead to a subclass of regularization networks, the well known Radial

Regular networks are determined by their trees

by Stephen J. Willson , 2009
"... Abstract. A rooted acyclic digraph N with labelled leaves displays a tree T when there exists a way to select a unique parent of each hybrid vertex resulting in the tree T. Let Tr(N) denote the set of all trees displayed by the network N. In general, there may be many other networks M such that Tr(M ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
(M) = Tr(N). A network is regular if it is isomorphic with its cover digraph. This paper shows that if N is regular, there is a procedure to reconstruct N given Tr(N). Hence if N and M are regular networks and Tr(N) = Tr(M), it follows that N = M, proving that a regular network is uniquely determined

Diagnosabilities of regular networks

by Guey-yun Chang, Gerard J. Chang, Gen-huey Chen - IEEE Transactions on Parallel and Distributed Systems
"... In this paper, we study diagnosabilities of multiprocessor systems under two diagnosis models: the PMC model and the comparison model. In each model, we further consider two different diagnosis strategies: the precise diagnosis strategy proposed by Preparata et al. and the pessimistic diagnosis stra ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
strategy proposed by Friedman. The main result of this paper is to determine diagnosabilities of regular networks with certain conditions, which include several widely used multiprocessor systems such as variants of hypercubes and many others.

Generalization Performance of Regularization Networks and Support . . .

by Robert C. Williamson, Alex J. Smola, Bernhard Schölkopf - IEEE TRANSACTIONS ON INFORMATION THEORY , 2001
"... We derive new bounds for the generalization error of kernel machines, such as support vector machines and related regularization networks by obtaining new bounds on their covering numbers. The proofs make use of a viewpoint that is apparently novel in the field of statistical learning theory. The hy ..."
Abstract - Cited by 79 (17 self) - Add to MetaCart
We derive new bounds for the generalization error of kernel machines, such as support vector machines and related regularization networks by obtaining new bounds on their covering numbers. The proofs make use of a viewpoint that is apparently novel in the field of statistical learning theory

Understanding Normal and Impaired Word Reading: Computational Principles in Quasi-Regular Domains

by David C. Plaut , James L. McClelland, Mark S. Seidenberg, Karalyn Patterson - PSYCHOLOGICAL REVIEW , 1996
"... We develop a connectionist approach to processing in quasi-regular domains, as exemplified by English word reading. A consideration of the shortcomings of a previous implementation (Seidenberg & McClelland, 1989, Psych. Rev.) in reading nonwords leads to the development of orthographic and phono ..."
Abstract - Cited by 613 (94 self) - Add to MetaCart
and phonological representations that capture better the relevant structure among the written and spoken forms of words. In a number of simulation experiments, networks using the new representations learn to read both regular and exception words, including low-frequency exception words, and yet are still able

Error and attack tolerance of complex networks

by Réka Albert, Hawoong Jeong, Albert-László Barabási , 2000
"... Many complex systems display a surprising degree of tolerance against errors. For example, relatively simple organisms grow, persist and reproduce despite drastic pharmaceutical or environmental interventions, an error tolerance attributed to the robustness of the underlying metabolic network [1]. C ..."
Abstract - Cited by 1013 (7 self) - Add to MetaCart
]. Complex communication networks [2] display a surprising degree of robustness: while key components regularly malfunction, local failures rarely lead to the loss of the global information-carrying ability of the network. The stability of these and other complex systems is often attributed to the redundant

Capacity of Ad Hoc Wireless Networks

by Jinyang Li, Charles Blake, Douglas S. J. De Couto, Hu Imm Lee, Robert Morris
"... Early simulation experience with wireless ad hoc networks suggests that their capacity can be surprisingly low, due to the requirement that nodes forward each others’ packets. The achievable capacity depends on network size, traffic patterns, and detailed local radio interactions. This paper examine ..."
Abstract - Cited by 636 (14 self) - Add to MetaCart
forwarding and the effect on capacity for several simple configurations and traffic patterns. While 802.11 discovers reasonably good schedules, we nonetheless observe capacities markedly less than optimal for very simple chain and lattice networks with very regular traffic patterns. We validate some

Internet time synchronization: The network time protocol

by D. L. Mills , 1989
"... This memo describes the Network Time Protocol (NTP) designed to distribute time information in a large, diverse internet system operating at speeds from mundane to lightwave. It uses a returnabletime architecture in which a distributed subnet of time servers operating in a self-organizing, hierarchi ..."
Abstract - Cited by 628 (15 self) - Add to MetaCart
This memo describes the Network Time Protocol (NTP) designed to distribute time information in a large, diverse internet system operating at speeds from mundane to lightwave. It uses a returnabletime architecture in which a distributed subnet of time servers operating in a self

Imagenet classification with deep convolutional neural networks.

by Alex Krizhevsky , Ilya Sutskever , Geoffrey E Hinton - In Advances in the Neural Information Processing System, , 2012
"... Abstract We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the pr ..."
Abstract - Cited by 1010 (11 self) - Add to MetaCart
Abstract We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than
Results 1 - 10 of 6,886