Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/107258
Title: Modularity as a means for complexity management in neural networks learning
Authors: Castillo Bolado, David 
Guerra-Artal, Cayetano 
Hernandez-Tejera, Mario 
UNESCO Clasification: 120304 Inteligencia artificial
Issue Date: 2019
Journal: ArXiv.org 
Abstract: Training a Neural Network (NN) with lots of parameters or intricate architectures creates undesired phenomena that complicate the optimization process. To address this issue we propose a first modular approach to NN design, wherein the NN is decomposed into a control module and several functional modules, implementing primitive operations. We illustrate the modular concept by comparing performances between a monolithic and a modular NN on a list sorting problem and show the benefits in terms of training speed, training stability and maintainability. We also discuss some questions that arise in modular NNs.
URI: http://hdl.handle.net/10553/107258
ISSN: 2331-8422
DOI: 10.48550/arXiv.1902.09240
Source: ArXiv.org [ISSN 2331-8422], 25 febrero 2019
Appears in Collections:Artículos
Thumbnail
Adobe PDF (1,12 MB)
Show full item record

Page view(s)

85
checked on Jun 25, 2022

Download(s)

35
checked on Jun 25, 2022

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.