MEMOCODE 2014 design contest: K-Nearest Neighbors with Mahalanobis distance metric

Peter Milder

doi:10.1109/MEMCOD.2014.6961861

MEMOCODE 2014 design contest: K-Nearest Neighbors with Mahalanobis distance metric

Peter Milder

Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

The MEMOCODE 2014 hardware/software codesign contest problem is k-Nearest Neighbor search using the Mahalanobis distance metric. Given a data set of points in multi-dimensional space, the goal is to find the k points that are nearest to any given point in that space (quantified with the given distance metric). Contestants were given one month to develop a system to perform the kNN search, aiming to maximize performance or cost-adjusted performance. The two winning teams, which have been invited to contribute papers describing their techniques, combined algorithmic and implementation optimizations. The pure-performance winners targeted the Convey HC-2ex hybrid FPGA/multicore system, while the winners for cost-adjusted performance targeted an Intel multicore.

Original language	English
Title of host publication	12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	198-200
Number of pages	3
ISBN (Electronic)	9781479953387
DOIs	https://doi.org/10.1109/MEMCOD.2014.6961861
State	Published - Nov 18 2014
Event	12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014 - Lausanne, Switzerland Duration: Oct 19 2014 → Oct 21 2014

Publication series

Name	12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014

Conference

Conference	12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014
Country/Territory	Switzerland
City	Lausanne
Period	10/19/14 → 10/21/14

Access to Document

10.1109/MEMCOD.2014.6961861

Cite this

Milder, P. (2014). MEMOCODE 2014 design contest: K-Nearest Neighbors with Mahalanobis distance metric. In 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014 (pp. 198-200). Article 6961861 (12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MEMCOD.2014.6961861

@inproceedings{8d6e252de1b944d591cfd1c9d087ff7e,

title = "MEMOCODE 2014 design contest: K-Nearest Neighbors with Mahalanobis distance metric",

abstract = "The MEMOCODE 2014 hardware/software codesign contest problem is k-Nearest Neighbor search using the Mahalanobis distance metric. Given a data set of points in multi-dimensional space, the goal is to find the k points that are nearest to any given point in that space (quantified with the given distance metric). Contestants were given one month to develop a system to perform the kNN search, aiming to maximize performance or cost-adjusted performance. The two winning teams, which have been invited to contribute papers describing their techniques, combined algorithmic and implementation optimizations. The pure-performance winners targeted the Convey HC-2ex hybrid FPGA/multicore system, while the winners for cost-adjusted performance targeted an Intel multicore.",

author = "Peter Milder",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014 ; Conference date: 19-10-2014 Through 21-10-2014",

year = "2014",

month = nov,

day = "18",

doi = "10.1109/MEMCOD.2014.6961861",

language = "English",

series = "12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "198--200",

booktitle = "12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014",

}

Milder, P 2014, MEMOCODE 2014 design contest: K-Nearest Neighbors with Mahalanobis distance metric. in 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014., 6961861, 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014, Institute of Electrical and Electronics Engineers Inc., pp. 198-200, 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014, Lausanne, Switzerland, 10/19/14. https://doi.org/10.1109/MEMCOD.2014.6961861

MEMOCODE 2014 design contest: K-Nearest Neighbors with Mahalanobis distance metric. / Milder, Peter.
12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 198-200 6961861 (12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - MEMOCODE 2014 design contest

T2 - 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014

AU - Milder, Peter

PY - 2014/11/18

Y1 - 2014/11/18

N2 - The MEMOCODE 2014 hardware/software codesign contest problem is k-Nearest Neighbor search using the Mahalanobis distance metric. Given a data set of points in multi-dimensional space, the goal is to find the k points that are nearest to any given point in that space (quantified with the given distance metric). Contestants were given one month to develop a system to perform the kNN search, aiming to maximize performance or cost-adjusted performance. The two winning teams, which have been invited to contribute papers describing their techniques, combined algorithmic and implementation optimizations. The pure-performance winners targeted the Convey HC-2ex hybrid FPGA/multicore system, while the winners for cost-adjusted performance targeted an Intel multicore.

AB - The MEMOCODE 2014 hardware/software codesign contest problem is k-Nearest Neighbor search using the Mahalanobis distance metric. Given a data set of points in multi-dimensional space, the goal is to find the k points that are nearest to any given point in that space (quantified with the given distance metric). Contestants were given one month to develop a system to perform the kNN search, aiming to maximize performance or cost-adjusted performance. The two winning teams, which have been invited to contribute papers describing their techniques, combined algorithmic and implementation optimizations. The pure-performance winners targeted the Convey HC-2ex hybrid FPGA/multicore system, while the winners for cost-adjusted performance targeted an Intel multicore.

UR - https://www.scopus.com/pages/publications/84916614014

U2 - 10.1109/MEMCOD.2014.6961861

DO - 10.1109/MEMCOD.2014.6961861

M3 - Conference contribution

AN - SCOPUS:84916614014

T3 - 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014

SP - 198

EP - 200

BT - 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 19 October 2014 through 21 October 2014

ER -

Milder P. MEMOCODE 2014 design contest: K-Nearest Neighbors with Mahalanobis distance metric. In 12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 198-200. 6961861. (12th ACM/IEEE International Conference on Methods and Models for System Design, MEMOCODE 2014). doi: 10.1109/MEMCOD.2014.6961861

MEMOCODE 2014 design contest: K-Nearest Neighbors with Mahalanobis distance metric

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this