Neural network training loss optimization utilizing the sliding innovation filter

Naseem Alsadi; Waleed Hilal; Onur Surucu; Alessandro Giuliano; Stephen A. Gadsden; John Yawney; Mohammad A. AlShabi

doi:10.1117/12.2619029

6 June 2022 Neural network training loss optimization utilizing the sliding innovation filter

Naseem Alsadi, Waleed Hilal, Onur Surucu, Alessandro Giuliano, Stephen A. Gadsden, John Yawney, Mohammad A. AlShabi

Proceedings Volume 12113, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV; 121131Z (2022) https://doi.org/10.1117/12.2619029
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Conference Poster

Abstract

Artificial feedforward neural networks (ANN) have been traditionally trained by backpropagation algorithms involving gradient descent algorithms. This is in order to optimize the network’s weights and parameters in the training phase to minimize the out of sample error in the output during testing. However, gradient descent (GD) has been proven to be slow and computationally inefficient in comparison with studies implementing the extended Kalman filter (EKF) and unscented Kalman filter (UKF) as optimizers in ANNs. In this paper, a new method of training ANNs is proposed utilizing the sliding innovation filter (SIF). The SIF by Gadsden et al. has demonstrated to be a more robust predictor-corrector than the Kalman filters, especially in ill-conditioned situations or the presence of modelling uncertainties. In this paper, we propose implementing the SIF as an optimizer for training ANNs. The ANN proposed is trained with the SIF to predict the Mackey-Glass Chaotic series, and results demonstrate that the proposed method results in improved computation time compared to current estimation strategies for training ANNs while achieving results comparable to a UKF-trained neural network.

Citation Download Citation

Naseem Alsadi, Waleed Hilal, Onur Surucu, Alessandro Giuliano, Stephen A. Gadsden, John Yawney, and Mohammad A. AlShabi "Neural network training loss optimization utilizing the sliding innovation filter", Proc. SPIE 12113, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV, 121131Z (6 June 2022); https://doi.org/10.1117/12.2619029

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