Evaluating the variance in convolutional neural network behavior stemming from randomness

Christopher Menart

doi:10.1117/12.2558227

24 April 2020 Evaluating the variance in convolutional neural network behavior stemming from randomness

Christopher Menart

Proceedings Volume 11394, Automatic Target Recognition XXX; 1139410 (2020) https://doi.org/10.1117/12.2558227
Event: SPIE Defense + Commercial Sensing, 2020, Online Only

Abstract

Deep neural networks are a powerful and versatile machine learning technique with strong performance on many tasks. A large variety of neural architectures and training algorithms have been published in the past decade, each attempting to improve aspects of performance and computational cost on specific tasks. But the performance of these methods can be chaotic. Not only does the behavior of a neural network vary significantly with respect to small algorithmic changes, but the same training algorithm, run multiple times, may produce models with different performance, due to multiple stochastic aspects of the training process. Replication experiments in deep neural network design is difficult in part for this reason. We perform empirical evaluations using the canonical task of image recognition with Convolutional Neural Networks to determine what degree of variation in neural network performance is due to random chance. This has implications for network tuning as well as for the evaluation of architecture and algorithm changes.

Citation Download Citation

Christopher Menart "Evaluating the variance in convolutional neural network behavior stemming from randomness", Proc. SPIE 11394, Automatic Target Recognition XXX, 1139410 (24 April 2020); https://doi.org/10.1117/12.2558227

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