Inferring convolutional neural networks' accuracies from their architectural characterizations

Duc Hoang; Jesse Hamer; Gabriel Perdue; Steven Young; Jonathan Miller; Anushree Ghosh

doi:10.1109/ICMLA.2019.00226

Inferring convolutional neural networks' accuracies from their architectural characterizations

Duc Hoang, Jesse Hamer, Gabriel Perdue, Steven Young, Jonathan Miller, Anushree Ghosh

Learning Systems

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

Abstract

The challenge of choosing an appropriate convolutional neural network (CNN) architecture for specific applications and different data sets is still poorly understood in the literature. This is problematic, since CNNs have shown strong promise for analyzing scientific data from many domains including particle imaging detectors. In this paper, we proposed a systematic language that is useful for comparison between different CNN's architectures before training time. This helps us predict whether a network can perform better than a certain threshold accuracy before training up to 70% accuracy using simple machine learning models. Additionally, we found a coefficient of determination of 0.966 for an Ordinary Least Squares model in a regression task to predict accuracy of a large population of networks.

Original language	English
Title of host publication	Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019
Editors	M. Arif Wani, Taghi M. Khoshgoftaar, Dingding Wang, Huanjing Wang, Naeem Seliya
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1388-1391
Number of pages	4
ISBN (Electronic)	9781728145495
DOIs	https://doi.org/10.1109/ICMLA.2019.00226
State	Published - Dec 2019
Event	18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 - Boca Raton, United States Duration: Dec 16 2019 → Dec 19 2019

Publication series

Name	Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

Conference

Conference	18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019
Country/Territory	United States
City	Boca Raton
Period	12/16/19 → 12/19/19

Funding

ACKNOWLEDGMENT We would like to thank the MINERvA collaboration for access to their simulated data sets for this analysis. MINERvA uses the resources of the Fermi National Accelerator Laboratory (Fermilab), a U.S. Department of Energy, Office of Science, HEP User Facility. Fermilab is managed by Fermi Research Alliance, LLC (FRA), acting under Contract No. DE-AC02-07CH11359, which included the MINERvA construction project. This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, Robinson Pino, program manager, under contract number DE-AC05-00OR22725. This research used resources of the Oak Ridge Leadership Computing Facility at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.

Keywords

Computer vision
Convolutional neural networks
High energy physics
Network architecture
Transfer domains

Access to Document

10.1109/ICMLA.2019.00226

Cite this

Hoang, D., Hamer, J., Perdue, G., Young, S., Miller, J., & Ghosh, A. (2019). Inferring convolutional neural networks' accuracies from their architectural characterizations. In M. A. Wani, T. M. Khoshgoftaar, D. Wang, H. Wang, & N. Seliya (Eds.), Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 (pp. 1388-1391). Article 8999151 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLA.2019.00226

Hoang, Duc ; Hamer, Jesse ; Perdue, Gabriel et al. / Inferring convolutional neural networks' accuracies from their architectural characterizations. Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. editor / M. Arif Wani ; Taghi M. Khoshgoftaar ; Dingding Wang ; Huanjing Wang ; Naeem Seliya. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1388-1391 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019).

@inproceedings{5359042df6344169a1b751e3c8a72729,

title = "Inferring convolutional neural networks' accuracies from their architectural characterizations",

abstract = "The challenge of choosing an appropriate convolutional neural network (CNN) architecture for specific applications and different data sets is still poorly understood in the literature. This is problematic, since CNNs have shown strong promise for analyzing scientific data from many domains including particle imaging detectors. In this paper, we proposed a systematic language that is useful for comparison between different CNN's architectures before training time. This helps us predict whether a network can perform better than a certain threshold accuracy before training up to 70% accuracy using simple machine learning models. Additionally, we found a coefficient of determination of 0.966 for an Ordinary Least Squares model in a regression task to predict accuracy of a large population of networks.",

keywords = "Computer vision, Convolutional neural networks, High energy physics, Network architecture, Transfer domains",

author = "Duc Hoang and Jesse Hamer and Gabriel Perdue and Steven Young and Jonathan Miller and Anushree Ghosh",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019 ; Conference date: 16-12-2019 Through 19-12-2019",

year = "2019",

month = dec,

doi = "10.1109/ICMLA.2019.00226",

language = "English",

series = "Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019",

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

pages = "1388--1391",

editor = "Wani, {M. Arif} and Khoshgoftaar, {Taghi M.} and Dingding Wang and Huanjing Wang and Naeem Seliya",

booktitle = "Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019",

}

Hoang, D, Hamer, J, Perdue, G, Young, S, Miller, J & Ghosh, A 2019, Inferring convolutional neural networks' accuracies from their architectural characterizations. in MA Wani, TM Khoshgoftaar, D Wang, H Wang & N Seliya (eds), Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019., 8999151, Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019, Institute of Electrical and Electronics Engineers Inc., pp. 1388-1391, 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019, Boca Raton, United States, 12/16/19. https://doi.org/10.1109/ICMLA.2019.00226

Inferring convolutional neural networks' accuracies from their architectural characterizations. / Hoang, Duc; Hamer, Jesse; Perdue, Gabriel et al.
Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. ed. / M. Arif Wani; Taghi M. Khoshgoftaar; Dingding Wang; Huanjing Wang; Naeem Seliya. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1388-1391 8999151 (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019).

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

TY - GEN

T1 - Inferring convolutional neural networks' accuracies from their architectural characterizations

AU - Hoang, Duc

AU - Hamer, Jesse

AU - Perdue, Gabriel

AU - Young, Steven

AU - Miller, Jonathan

AU - Ghosh, Anushree

PY - 2019/12

Y1 - 2019/12

N2 - The challenge of choosing an appropriate convolutional neural network (CNN) architecture for specific applications and different data sets is still poorly understood in the literature. This is problematic, since CNNs have shown strong promise for analyzing scientific data from many domains including particle imaging detectors. In this paper, we proposed a systematic language that is useful for comparison between different CNN's architectures before training time. This helps us predict whether a network can perform better than a certain threshold accuracy before training up to 70% accuracy using simple machine learning models. Additionally, we found a coefficient of determination of 0.966 for an Ordinary Least Squares model in a regression task to predict accuracy of a large population of networks.

AB - The challenge of choosing an appropriate convolutional neural network (CNN) architecture for specific applications and different data sets is still poorly understood in the literature. This is problematic, since CNNs have shown strong promise for analyzing scientific data from many domains including particle imaging detectors. In this paper, we proposed a systematic language that is useful for comparison between different CNN's architectures before training time. This helps us predict whether a network can perform better than a certain threshold accuracy before training up to 70% accuracy using simple machine learning models. Additionally, we found a coefficient of determination of 0.966 for an Ordinary Least Squares model in a regression task to predict accuracy of a large population of networks.

KW - Computer vision

KW - Convolutional neural networks

KW - High energy physics

KW - Network architecture

KW - Transfer domains

UR - http://www.scopus.com/inward/record.url?scp=85080960827&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2019.00226

DO - 10.1109/ICMLA.2019.00226

M3 - Conference contribution

AN - SCOPUS:85080960827

T3 - Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

SP - 1388

EP - 1391

BT - Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

A2 - Wani, M. Arif

A2 - Khoshgoftaar, Taghi M.

A2 - Wang, Dingding

A2 - Wang, Huanjing

A2 - Seliya, Naeem

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019

Y2 - 16 December 2019 through 19 December 2019

ER -

Hoang D, Hamer J, Perdue G, Young S, Miller J, Ghosh A. Inferring convolutional neural networks' accuracies from their architectural characterizations. In Wani MA, Khoshgoftaar TM, Wang D, Wang H, Seliya N, editors, Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1388-1391. 8999151. (Proceedings - 18th IEEE International Conference on Machine Learning and Applications, ICMLA 2019). doi: 10.1109/ICMLA.2019.00226

Inferring convolutional neural networks' accuracies from their architectural characterizations

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this