Saved in:
Bibliographic Details
Main Authors: Van Egmond, Zachary Yetman, Rodrigues, Luis
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.08267
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929592344772608
author Van Egmond, Zachary Yetman
Rodrigues, Luis
author_facet Van Egmond, Zachary Yetman
Rodrigues, Luis
contents This paper provides a least squares formulation for the training of a 2-layer convolutional neural network using quadratic activation functions, a 2-norm loss function, and no regularization term. Using this method, an analytic expression for the globally optimal weights is obtained alongside a quadratic input-output equation for the network. These properties make the network a viable tool in system theory by enabling further analysis, such as the sensitivity of the output to perturbations in the input, which is crucial for safety-critical systems such as aircraft or autonomous vehicles. The least squares method is compared to previously proposed strategies for training quadratic networks and to a back-propagation-trained ReLU network. The proposed method is applied to a system identification problem and a GPS position estimation problem. The least squares network is shown to have a significantly reduced training time with minimal compromises on prediction accuracy alongside the advantages of having an analytic input-output equation. Although these results only apply to 2-layer networks, this paper motivates the exploration of deeper quadratic networks in the context of system theory.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08267
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Least Squares Training of Quadratic Convolutional Neural Networks with Applications to System Theory
Van Egmond, Zachary Yetman
Rodrigues, Luis
Machine Learning
This paper provides a least squares formulation for the training of a 2-layer convolutional neural network using quadratic activation functions, a 2-norm loss function, and no regularization term. Using this method, an analytic expression for the globally optimal weights is obtained alongside a quadratic input-output equation for the network. These properties make the network a viable tool in system theory by enabling further analysis, such as the sensitivity of the output to perturbations in the input, which is crucial for safety-critical systems such as aircraft or autonomous vehicles. The least squares method is compared to previously proposed strategies for training quadratic networks and to a back-propagation-trained ReLU network. The proposed method is applied to a system identification problem and a GPS position estimation problem. The least squares network is shown to have a significantly reduced training time with minimal compromises on prediction accuracy alongside the advantages of having an analytic input-output equation. Although these results only apply to 2-layer networks, this paper motivates the exploration of deeper quadratic networks in the context of system theory.
title Least Squares Training of Quadratic Convolutional Neural Networks with Applications to System Theory
topic Machine Learning
url https://arxiv.org/abs/2411.08267