Synergistic reconfiguration of adaptive precision chemical classifiers

Michael Gilberti; Alex Doboli

doi:10.1109/AHS.2009.49

Synergistic reconfiguration of adaptive precision chemical classifiers

Michael Gilberti
, Alex Doboli

Electrical Engineering

Stony Brook University

Stony Brook University

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

1 Scopus citations

Abstract

We present parallel implementations of a multilayer perceptron that uses reduced variable bit width hardware to improve resource utilization while still providing known levels of accuracy. We show results for a chemical classification application and introduce ways in which to take advantage of the capabilities of a reconfigurable device. We show how the optimized circuit can be used synergistically in parallel with other classifiers for added capability and alone for fault tolerance and saving power.

Original language	English
Title of host publication	Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009
Pages	181-188
Number of pages	8
DOIs	https://doi.org/10.1109/AHS.2009.49
State	Published - 2009
Event	2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009 - San Francisco, CA, United States Duration: Jul 29 2009 → Aug 1 2009

Publication series

Name	Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009

Conference

Conference	2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009
Country/Territory	United States
City	San Francisco, CA
Period	07/29/09 → 08/1/09

Access to Document

10.1109/AHS.2009.49

Cite this

@inproceedings{068e5a06a05845f3bd4d089e4c79ea80,

title = "Synergistic reconfiguration of adaptive precision chemical classifiers",

abstract = "We present parallel implementations of a multilayer perceptron that uses reduced variable bit width hardware to improve resource utilization while still providing known levels of accuracy. We show results for a chemical classification application and introduce ways in which to take advantage of the capabilities of a reconfigurable device. We show how the optimized circuit can be used synergistically in parallel with other classifiers for added capability and alone for fault tolerance and saving power.",

author = "Michael Gilberti and Alex Doboli",

year = "2009",

doi = "10.1109/AHS.2009.49",

language = "English",

isbn = "9780769537146",

series = "Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009",

pages = "181--188",

booktitle = "Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009",

note = "2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009 ; Conference date: 29-07-2009 Through 01-08-2009",

}

Gilberti, M & Doboli, A 2009, Synergistic reconfiguration of adaptive precision chemical classifiers. in Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009., 5325456, Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009, pp. 181-188, 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009, San Francisco, CA, United States, 07/29/09. https://doi.org/10.1109/AHS.2009.49

Synergistic reconfiguration of adaptive precision chemical classifiers. / Gilberti, Michael; Doboli, Alex.
Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009. 2009. p. 181-188 5325456 (Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009).

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

TY - GEN

T1 - Synergistic reconfiguration of adaptive precision chemical classifiers

AU - Gilberti, Michael

AU - Doboli, Alex

PY - 2009

Y1 - 2009

N2 - We present parallel implementations of a multilayer perceptron that uses reduced variable bit width hardware to improve resource utilization while still providing known levels of accuracy. We show results for a chemical classification application and introduce ways in which to take advantage of the capabilities of a reconfigurable device. We show how the optimized circuit can be used synergistically in parallel with other classifiers for added capability and alone for fault tolerance and saving power.

AB - We present parallel implementations of a multilayer perceptron that uses reduced variable bit width hardware to improve resource utilization while still providing known levels of accuracy. We show results for a chemical classification application and introduce ways in which to take advantage of the capabilities of a reconfigurable device. We show how the optimized circuit can be used synergistically in parallel with other classifiers for added capability and alone for fault tolerance and saving power.

UR - https://www.scopus.com/pages/publications/72849130914

U2 - 10.1109/AHS.2009.49

DO - 10.1109/AHS.2009.49

M3 - Conference contribution

SN - 9780769537146

T3 - Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009

SP - 181

EP - 188

BT - Proceedings - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009

T2 - 2009 NASA/ESA Conference on Adaptive Hardware and Systems, AHS 2009

Y2 - 29 July 2009 through 1 August 2009

ER -

Synergistic reconfiguration of adaptive precision chemical classifiers

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this