Results 1  10
of
363,050
Performance analysis of kary ncube interconnection networks
 IEEE Transactions on Computers
, 1990
"... AbstmctVLSI communication networks are wirelimited. The cost of a network is not a function of the number of switches required, but rather a function of the wiring density required to construct the network. This paper analyzes communication networks of varying dimension under the assumption of co ..."
Abstract

Cited by 355 (18 self)
 Add to MetaCart
of constant wire bisection. Expressions for the latency, average case throughput, and hotspot throughput of kary ncube networks with constant bisection are derived that agree closely with experimental measurements. It is shown that lowdimensional networks (e.g., tori) have lower latency and higher hot
A fast learning algorithm for deep belief nets
 Neural Computation
, 2006
"... We show how to use “complementary priors ” to eliminate the explaining away effects that make inference difficult in denselyconnected belief nets that have many hidden layers. Using complementary priors, we derive a fast, greedy algorithm that can learn deep, directed belief networks one layer at a ..."
Abstract

Cited by 929 (49 self)
 Add to MetaCart
very good generative model of the joint distribution of handwritten digit images and their labels. This generative model gives better digit classification than the best discriminative learning algorithms. The lowdimensional manifolds on which the digits lie are modelled by long ravines in the free
LOWDIMENSIONAL
"... The LDHD program was devoted to the development of methodological, theoretical, and computational treatment of highdimensional mathematical and statistical models. Possibly limited amounts of available data pose added challenges in high dimensions. The program addressed these challenges by focusing ..."
Abstract
 Add to MetaCart
by focusing on lowdimensional structures that approximate or encapsulate given highdimensional data. Cutting edge methods of dimension reduction were brought together from probability and statistics, geometry, topology, and computer science. These techniques included variable selection, graphical modeling
A Growing Neural Gas Network Learns Topologies
 Advances in Neural Information Processing Systems 7
, 1995
"... An incremental network model is introduced which is able to learn the important topological relations in a given set of input vectors by means of a simple Hebblike learning rule. In contrast to previous approaches like the "neural gas" method of Martinetz and Schulten (1991, 1994), this m ..."
Abstract

Cited by 394 (5 self)
 Add to MetaCart
data is available but no information on the desired output. What can the goal of learning be in this situation? One possible objective is dimensionality reduction: finding a lowdimensional subspace of the input vector space containing most or all of the input data. Linear subspaces with this property
Insertion sequences
 Microbiol Mol. Biol. Rev
, 1998
"... These include: Receive: RSS Feeds, eTOCs, free email alerts (when new articles cite this article), more» Downloaded from ..."
Abstract

Cited by 426 (3 self)
 Add to MetaCart
These include: Receive: RSS Feeds, eTOCs, free email alerts (when new articles cite this article), more» Downloaded from
Learning as Extraction of LowDimensional Representations
 Mechanisms of Perceptual Learning
, 1996
"... Psychophysical findings accumulated over the past several decades indicate that perceptual tasks such as similarity judgment tend to be performed on a lowdimensional representation of the sensory data. Low dimensionality is especially important for learning, as the number of examples required for a ..."
Abstract

Cited by 35 (8 self)
 Add to MetaCart
Psychophysical findings accumulated over the past several decades indicate that perceptual tasks such as similarity judgment tend to be performed on a lowdimensional representation of the sensory data. Low dimensionality is especially important for learning, as the number of examples required
LowDimensional Embedding with Extra Information
, 2004
"... A frequently arising problem in computational geometry is when a physical structure, such as an adhoc wireless sensor network or a protein backbone, can measure local information about its geometry (e.g., distances, angles, and/or orientations), and the goal is to reconstruct the global geometry fr ..."
Abstract

Cited by 20 (3 self)
 Add to MetaCart
A frequently arising problem in computational geometry is when a physical structure, such as an adhoc wireless sensor network or a protein backbone, can measure local information about its geometry (e.g., distances, angles, and/or orientations), and the goal is to reconstruct the global geometry
Opening the Black Box: Lowdimensional . . .
"... Equal contribution Recurrent neural networks (RNNs) are useful tools for learning nonlinear relationships between timevarying inputs and outputs with complex temporal dependencies. Recently developed algorithms have been successful at training RNNs to perform a wide variety of tasks, but the resu ..."
Abstract
 Add to MetaCart
Equal contribution Recurrent neural networks (RNNs) are useful tools for learning nonlinear relationships between timevarying inputs and outputs with complex temporal dependencies. Recently developed algorithms have been successful at training RNNs to perform a wide variety of tasks
Navigating LowDimensional and Hierarchical Population Networks
 IN 14TH EUROPEAN SYMPOSIUM ON ALGORITHM (ESA), LNCS 4168
, 2006
"... Social networks are navigable small worlds, in which two arbitrary people are likely connected by a short path of intermediate friends that can be found by a “decentralized” routing algorithm using only local information. We develop a model of social networks based on an arbitrary metric space of po ..."
Abstract

Cited by 10 (4 self)
 Add to MetaCart
Social networks are navigable small worlds, in which two arbitrary people are likely connected by a short path of intermediate friends that can be found by a “decentralized” routing algorithm using only local information. We develop a model of social networks based on an arbitrary metric space
Results 1  10
of
363,050