Please use this identifier to cite or link to this item:
Title: Modularity as a means for complexity management in neural networks learning
Authors: Castillo-Bolado, D.
Guerra-Artal, C. 
Hernandez-Tejera, M. 
UNESCO Clasification: 120304 Inteligencia artificial
Issue Date: 2019
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.
ISSN: 2331-8422
Source: [ISSN 2331-8422], 25 febrero 2019
Appears in Collections:Artículo preliminar
Adobe PDF (1,12 MB)
Show full item record

Google ScholarTM



Export metadata

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