Low-complexity convolutional neural networks for automatic target recognition

Dbouk, Hassan

Permalink

https://hdl.handle.net/2142/108091 Copy

Description

Title

Low-complexity convolutional neural networks for automatic target recognition

Author(s)

Dbouk, Hassan

Issue Date

2020-03-11

Director of Research (if dissertation) or Advisor (if thesis)

Shanbhag, Naresh R

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• deep learning
• neural networks
• automatic target recognition
• synthetic aperture radar
• quantization

Abstract

Over the decades, several algorithms have been proposed for designing automatic target recognition systems based on synthetic aperture radar imagery. Recently, with the rise of Deep Learning, there has been growing interest in developing neural network based automatic target recognition systems for synthetic aperture radar applications. However, these networks are typically complex in terms of storage and computation which inhibits their deployment in the field, where such resources are heavily constrained. In order to reduce the cost of implementing these networks, in this thesis we develop a set of compact network architectures and train them in fixed-point. Our proposed method achieves an overall 984× reduction in terms of storage requirements and 71× reduction in terms of computational complexity compared to state-of-the-art convolutional neural networks for automatic target recognition, while maintaining a classification accuracy of >99% on the MSTAR dataset.

Graduation Semester

2020-05

Type of Resource

Thesis

Permalink

http://hdl.handle.net/2142/108091

Copyright and License Information

Copyright 2020 Hassan Dbouk

Owning Collections