Saved in:
Bibliographic Details
Main Authors: Origer, Sebastien, Izzo, Dario
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.18084
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929362121523200
author Origer, Sebastien
Izzo, Dario
author_facet Origer, Sebastien
Izzo, Dario
contents Inspired by the versatility of sinusoidal representation networks (SIRENs), we present a modified Guidance & Control Networks (G&CNETs) variant using periodic activation functions in the hidden layers. We demonstrate that the resulting G&CNETs train faster and achieve a lower overall training error on three different control scenarios on which G&CNETs have been tested previously. A preliminary analysis is presented in an attempt to explain the superior performance of the SIREN architecture for the particular types of tasks that G&CNETs excel on.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18084
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Guidance and Control Networks with Periodic Activation Functions
Origer, Sebastien
Izzo, Dario
Machine Learning
Inspired by the versatility of sinusoidal representation networks (SIRENs), we present a modified Guidance & Control Networks (G&CNETs) variant using periodic activation functions in the hidden layers. We demonstrate that the resulting G&CNETs train faster and achieve a lower overall training error on three different control scenarios on which G&CNETs have been tested previously. A preliminary analysis is presented in an attempt to explain the superior performance of the SIREN architecture for the particular types of tasks that G&CNETs excel on.
title Guidance and Control Networks with Periodic Activation Functions
topic Machine Learning
url https://arxiv.org/abs/2405.18084