Quantized wavelet scattering networks for signal classification

Maxine R. Fox, Raghu G. Raj, Ram Mohan Narayanan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

While convolutional neural networks (CNNs) are powerful tools in machine learning, their construction is far from a science. In addition, instantiations of CNNs are highly memory expensive and typically require large training sets. Wavelet scattering networks (WSNs) could provide a simple means of testing quantization schemes for CNNs, without the added complexity of adjustable parameters. Using the MSTAR database, the performance of a WSN in combination with several quantization schemes is examined.

Original languageEnglish (US)
Title of host publicationRadar Sensor Technology XXIII
EditorsKenneth I. Ranney, Armin Doerry
PublisherSPIE
ISBN (Electronic)9781510626713
DOIs
StatePublished - Jan 1 2019
EventRadar Sensor Technology XXIII 2019 - Baltimore, United States
Duration: Apr 15 2019Apr 17 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11003
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceRadar Sensor Technology XXIII 2019
CountryUnited States
CityBaltimore
Period4/15/194/17/19

Fingerprint

Wavelets
Scattering
Neural Networks
Neural networks
Quantization
scattering
Learning systems
Machine Learning
machine learning
Data storage equipment
Testing
education
Training

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Fox, M. R., Raj, R. G., & Narayanan, R. M. (2019). Quantized wavelet scattering networks for signal classification. In K. I. Ranney, & A. Doerry (Eds.), Radar Sensor Technology XXIII [110030V] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11003). SPIE. https://doi.org/10.1117/12.2519659
Fox, Maxine R. ; Raj, Raghu G. ; Narayanan, Ram Mohan. / Quantized wavelet scattering networks for signal classification. Radar Sensor Technology XXIII. editor / Kenneth I. Ranney ; Armin Doerry. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{82d821d2d5e243a0b27191f325ede703,
title = "Quantized wavelet scattering networks for signal classification",
abstract = "While convolutional neural networks (CNNs) are powerful tools in machine learning, their construction is far from a science. In addition, instantiations of CNNs are highly memory expensive and typically require large training sets. Wavelet scattering networks (WSNs) could provide a simple means of testing quantization schemes for CNNs, without the added complexity of adjustable parameters. Using the MSTAR database, the performance of a WSN in combination with several quantization schemes is examined.",
author = "Fox, {Maxine R.} and Raj, {Raghu G.} and Narayanan, {Ram Mohan}",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2519659",
language = "English (US)",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Ranney, {Kenneth I.} and Armin Doerry",
booktitle = "Radar Sensor Technology XXIII",
address = "United States",

}

Fox, MR, Raj, RG & Narayanan, RM 2019, Quantized wavelet scattering networks for signal classification. in KI Ranney & A Doerry (eds), Radar Sensor Technology XXIII., 110030V, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11003, SPIE, Radar Sensor Technology XXIII 2019, Baltimore, United States, 4/15/19. https://doi.org/10.1117/12.2519659

Quantized wavelet scattering networks for signal classification. / Fox, Maxine R.; Raj, Raghu G.; Narayanan, Ram Mohan.

Radar Sensor Technology XXIII. ed. / Kenneth I. Ranney; Armin Doerry. SPIE, 2019. 110030V (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11003).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Quantized wavelet scattering networks for signal classification

AU - Fox, Maxine R.

AU - Raj, Raghu G.

AU - Narayanan, Ram Mohan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - While convolutional neural networks (CNNs) are powerful tools in machine learning, their construction is far from a science. In addition, instantiations of CNNs are highly memory expensive and typically require large training sets. Wavelet scattering networks (WSNs) could provide a simple means of testing quantization schemes for CNNs, without the added complexity of adjustable parameters. Using the MSTAR database, the performance of a WSN in combination with several quantization schemes is examined.

AB - While convolutional neural networks (CNNs) are powerful tools in machine learning, their construction is far from a science. In addition, instantiations of CNNs are highly memory expensive and typically require large training sets. Wavelet scattering networks (WSNs) could provide a simple means of testing quantization schemes for CNNs, without the added complexity of adjustable parameters. Using the MSTAR database, the performance of a WSN in combination with several quantization schemes is examined.

UR - http://www.scopus.com/inward/record.url?scp=85072599600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072599600&partnerID=8YFLogxK

U2 - 10.1117/12.2519659

DO - 10.1117/12.2519659

M3 - Conference contribution

AN - SCOPUS:85072599600

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Radar Sensor Technology XXIII

A2 - Ranney, Kenneth I.

A2 - Doerry, Armin

PB - SPIE

ER -

Fox MR, Raj RG, Narayanan RM. Quantized wavelet scattering networks for signal classification. In Ranney KI, Doerry A, editors, Radar Sensor Technology XXIII. SPIE. 2019. 110030V. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2519659