Results 1  10
of
716,236
The pyramid match kernel: Discriminative classification with sets of image features
 IN ICCV
, 2005
"... Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernelbased classification methods can learn complex decision boundaries, but a kernel over unordered set inputs must somehow solve for correspondenc ..."
Abstract

Cited by 544 (29 self)
 Add to MetaCart
for correspondences – generally a computationally expensive task that becomes impractical for large set sizes. We present a new fast kernel function which maps unordered feature sets to multiresolution histograms and computes a weighted histogram intersection in this space. This “pyramid match” computation is linear
Tradeoff to minimize extracomputations and stopping criterion tests for parallel iterative schemes
 In PMAA’04 Parallel Matrix Algorithms and Applications. CIRM
, 2004
"... tests for parallel iterative schemes ..."
A Comparison of Dynamic Branch Predictors that use Two Levels of Branch History
 in Proceedings of the 20th Annual International Symposium on Computer Architecture
, 1993
"... Recent attention to speculative execution as a mechanism for increasing performance of single instruction streams has demanded substantially better branch prediction than what has been previously available. We [1, 2] and Pan, So, and Rahmeh [4] have both proposed variations of the same aggressive dy ..."
Abstract

Cited by 279 (9 self)
 Add to MetaCart
Recent attention to speculative execution as a mechanism for increasing performance of single instruction streams has demanded substantially better branch prediction than what has been previously available. We [1, 2] and Pan, So, and Rahmeh [4] have both proposed variations of the same aggressive dynamic branch predictor for handling those needs. We call the basic model TwoLevel Adaptive Branch Prediction; Pan, So, and Rahmeh call it Correlation Branch Prediction. In this paper, we adopt the terminology of [2] and show that there are really nine variations of the same basic model. We compare the nine variations with respect to the amount of history information kept. We study the effects of different branch history lengths and pattern history table configurations. Finally, we evaluate the cost effectiveness of the nine variations. 1 Introduction With the current movement toward deeper pipelines and wider issue rates, extremely high branch prediction accuracy becomes critical because a...
Efficient Search for Approximate Nearest Neighbor in High Dimensional Spaces
, 1998
"... We address the problem of designing data structures that allow efficient search for approximate nearest neighbors. More specifically, given a database consisting of a set of vectors in some high dimensional Euclidean space, we want to construct a spaceefficient data structure that would allow us to ..."
Abstract

Cited by 215 (9 self)
 Add to MetaCart
is polynomial in the size of the database, and search algorithms that run in time nearly linear or nearly quadratic in the dimension (depending on the case; the extra factors are polylogarithmic in the size of the database). Computer Science Department, Technion  IIT, Haifa 32000, Israel. Email: eyalk
Support vector domain description
 Pattern Recognition Letters
, 1999
"... This paper shows the use of a data domain description method, inspired by the support vector machine by Vapnik, called the support vector domain description (SVDD). This data description can be used for novelty or outlier detection. A spherically shaped decision boundary around a set of objects is c ..."
Abstract

Cited by 180 (9 self)
 Add to MetaCart
is constructed by a set of support vectors describing the sphere boundary. It has the possibility of transforming the data to new feature spaces without much extra computational cost. By using the transformed data, this SVDD can obtain more ¯exible and more accurate data descriptions. The error of the ®rst kind
Computing the shortest path: A* search meets graph theory
, 2005
"... We study the problem of finding a shortest path between two vertices in a directed graph. This is an important problem with many applications, including that of computing driving directions. We allow preprocessing the graph using a linear amount of extra space to store auxiliary information, and usi ..."
Abstract

Cited by 167 (8 self)
 Add to MetaCart
We study the problem of finding a shortest path between two vertices in a directed graph. This is an important problem with many applications, including that of computing driving directions. We allow preprocessing the graph using a linear amount of extra space to store auxiliary information
Bounds on universal extra dimensions
 Phys. Rev
"... We show that the bound from the electroweak data on the size of extra dimensions accessible to all the standard model fields is rather loose. These “universal” extra dimensions could have a compactification scale as low as 300 GeV for one extra dimension. This is because the KaluzaKlein number is c ..."
Abstract

Cited by 44 (0 self)
 Add to MetaCart
We show that the bound from the electroweak data on the size of extra dimensions accessible to all the standard model fields is rather loose. These “universal” extra dimensions could have a compactification scale as low as 300 GeV for one extra dimension. This is because the KaluzaKlein number
EXTRA REFERENCES:
"... COURSE CATALOG DESCRIPTION: ECE 495/595 – Reconfigurable Computing (4 credits) Development of components and techniques needed to design basic digital circuits and systems for controllers, computers, communication and related applications. Design and analysis of combinational and sequential logic ci ..."
Abstract
 Add to MetaCart
COURSE CATALOG DESCRIPTION: ECE 495/595 – Reconfigurable Computing (4 credits) Development of components and techniques needed to design basic digital circuits and systems for controllers, computers, communication and related applications. Design and analysis of combinational and sequential logic
EXTRA DIMENSIONS
"... explanation of terms used and discussion of significant model dependence of following limits, see the “Extra Dimensions Review.” Limits are expressed in conventions of of Giudice, Rattazzi, and Wells as explained in the Review. Footnotes describe originally quoted limit. n indicates the number of ex ..."
Abstract
 Add to MetaCart
explanation of terms used and discussion of significant model dependence of following limits, see the “Extra Dimensions Review.” Limits are expressed in conventions of of Giudice, Rattazzi, and Wells as explained in the Review. Footnotes describe originally quoted limit. n indicates the number
Results 1  10
of
716,236