Semi-random deep neural networks for near real-time target classification

Humza Syed; Ryan Bryla; Uttam Kumar Majumder; Dhireesha Kudithipudi

doi:10.1117/12.2520237

31 May 2019 Semi-random deep neural networks for near real-time target classification

Humza Syed, Ryan Bryla, Uttam Kumar Majumder, Dhireesha Kudithipudi

Proceedings Volume 10987, Algorithms for Synthetic Aperture Radar Imagery XXVI; 109870E (2019) https://doi.org/10.1117/12.2520237
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

In recent years deep neural networks have shown great advances in image processing tasks. For modern datasets, these networks require long training times due to backpropagation, high amount of computational resources for weight updates, and memory intensive weight storage. Exploiting randomness during the training of deep neural networks can mitigate these concerns by reducing the computational costs without sacrificing network performance. However, a fully randomized network has limitations for real-time target classification as it leads to poor performance. Therefore we are motivated in using semi-random deep neural networks to exploit random fixed weights. In this paper, we demonstrate that semi-random deep neural networks can achieve near real-time training with comparable accuracies to conventional deep neural networks models. We find that these networks are enhanced by the usage of skip connections and train rapidly at the cost of dense memory usage. With greater memory resources available, these networks can train on larger datasets at a fraction of the training time costs. These semi-random deep neural network architectures open up an avenue for further research in utilizing random fixed weights in neural networks.

Conference Presentation

Citation Download Citation

Humza Syed, Ryan Bryla, Uttam Kumar Majumder, and Dhireesha Kudithipudi "Semi-random deep neural networks for near real-time target classification", Proc. SPIE 10987, Algorithms for Synthetic Aperture Radar Imagery XXVI, 109870E (31 May 2019); https://doi.org/10.1117/12.2520237

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available