Ranking the parameters of deep neural networks using the fisher information

Ming Tu; Visar Berisha; Martin Woolf; Jae-sun Seo; Yu Cao

doi:10.1109/ICASSP.2016.7472157

Ranking the parameters of deep neural networks using the fisher information

Ming Tu, Visar Berisha, Martin Woolf, Jae-sun Seo, Yu Cao

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

7 Scopus citations

Abstract

The large number of parameters in deep neural networks (DNNs) often makes them prohibitive for low-power devices, such as field-programmable gate arrays (FPGA). In this paper, we propose a method to determine the relative importance of all network parameters by measuring the amount of information that the network output carries about each of the parameters - the Fisher Information. Based on the importance ranking, we design a complexity reduction scheme that discards unimportant parameters and assigns more quantization bits to more important parameters. For evaluation, we construct a deep autoencoder and learn a non-linear dimensionality reduction scheme for accelerometer data measuring the gait of individuals with Parkinson's disease. Experimental results confirm that the proposed ranking method can help reduce the complexity of the network with minimal impact on performance.

Original language	English (US)
Title of host publication	2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2647-2651
Number of pages	5
Volume	2016-May
ISBN (Electronic)	9781479999880
DOIs	https://doi.org/10.1109/ICASSP.2016.7472157
State	Published - May 18 2016
Event	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China Duration: Mar 20 2016 → Mar 25 2016

Other

Other	41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
Country	China
City	Shanghai
Period	3/20/16 → 3/25/16

Keywords

complexity reduction
deep neural networks
Fisher Information
FPGA
pruning
quantization

ASJC Scopus subject areas

Signal Processing
Software
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2016.7472157

Fingerprint Dive into the research topics of 'Ranking the parameters of deep neural networks using the fisher information'. Together they form a unique fingerprint.

Cite this

Tu, M., Berisha, V., Woolf, M., Seo, J., & Cao, Y. (2016). Ranking the parameters of deep neural networks using the fisher information. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (Vol. 2016-May, pp. 2647-2651). [7472157] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7472157

Ranking the parameters of deep neural networks using the fisher information. / Tu, Ming; Berisha, Visar; Woolf, Martin; Seo, Jae-sun ; Cao, Yu.

2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. p. 2647-2651 7472157.

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

Tu, M, Berisha, V, Woolf, M, Seo, J & Cao, Y 2016, Ranking the parameters of deep neural networks using the fisher information. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. vol. 2016-May, 7472157, Institute of Electrical and Electronics Engineers Inc., pp. 2647-2651, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 3/20/16. https://doi.org/10.1109/ICASSP.2016.7472157

@inproceedings{272a5f547fe54589bef83d66524c50c5,

title = "Ranking the parameters of deep neural networks using the fisher information",

abstract = "The large number of parameters in deep neural networks (DNNs) often makes them prohibitive for low-power devices, such as field-programmable gate arrays (FPGA). In this paper, we propose a method to determine the relative importance of all network parameters by measuring the amount of information that the network output carries about each of the parameters - the Fisher Information. Based on the importance ranking, we design a complexity reduction scheme that discards unimportant parameters and assigns more quantization bits to more important parameters. For evaluation, we construct a deep autoencoder and learn a non-linear dimensionality reduction scheme for accelerometer data measuring the gait of individuals with Parkinson's disease. Experimental results confirm that the proposed ranking method can help reduce the complexity of the network with minimal impact on performance.",

keywords = "complexity reduction, deep neural networks, Fisher Information, FPGA, pruning, quantization",

author = "Ming Tu and Visar Berisha and Martin Woolf and Jae-sun Seo and Yu Cao",

year = "2016",

month = may,

day = "18",

doi = "10.1109/ICASSP.2016.7472157",

language = "English (US)",

volume = "2016-May",

pages = "2647--2651",

booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",

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

address = "United States",

note = "41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 ; Conference date: 20-03-2016 Through 25-03-2016",

}

TY - GEN

T1 - Ranking the parameters of deep neural networks using the fisher information

AU - Tu, Ming

AU - Berisha, Visar

AU - Woolf, Martin

AU - Seo, Jae-sun

AU - Cao, Yu

PY - 2016/5/18

Y1 - 2016/5/18

N2 - The large number of parameters in deep neural networks (DNNs) often makes them prohibitive for low-power devices, such as field-programmable gate arrays (FPGA). In this paper, we propose a method to determine the relative importance of all network parameters by measuring the amount of information that the network output carries about each of the parameters - the Fisher Information. Based on the importance ranking, we design a complexity reduction scheme that discards unimportant parameters and assigns more quantization bits to more important parameters. For evaluation, we construct a deep autoencoder and learn a non-linear dimensionality reduction scheme for accelerometer data measuring the gait of individuals with Parkinson's disease. Experimental results confirm that the proposed ranking method can help reduce the complexity of the network with minimal impact on performance.

AB - The large number of parameters in deep neural networks (DNNs) often makes them prohibitive for low-power devices, such as field-programmable gate arrays (FPGA). In this paper, we propose a method to determine the relative importance of all network parameters by measuring the amount of information that the network output carries about each of the parameters - the Fisher Information. Based on the importance ranking, we design a complexity reduction scheme that discards unimportant parameters and assigns more quantization bits to more important parameters. For evaluation, we construct a deep autoencoder and learn a non-linear dimensionality reduction scheme for accelerometer data measuring the gait of individuals with Parkinson's disease. Experimental results confirm that the proposed ranking method can help reduce the complexity of the network with minimal impact on performance.

KW - complexity reduction

KW - deep neural networks

KW - Fisher Information

KW - FPGA

KW - pruning

KW - quantization

UR - http://www.scopus.com/inward/record.url?scp=84973402931&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973402931&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7472157

DO - 10.1109/ICASSP.2016.7472157

M3 - Conference contribution

AN - SCOPUS:84973402931

VL - 2016-May

SP - 2647

EP - 2651

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016

Y2 - 20 March 2016 through 25 March 2016

ER -