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, David Alejandro 
Guerra, Cayetano 
Hernández Tejera, Mario 
UNESCO Clasification: 120304 Inteligencia artificial
Issue Date: 2019
Journal: CEUR Workshop Proceedings 
Conference: 2019 AAAI Spring Symposium on Combining Machine Learning with Knowledge Engineering, AAAI-MAKE 2019 
Abstract: Training a Neural Network (NN) with lots of parameters orintricate architectures creates undesired phenomena that com-plicate the optimization process. To address this issue we pro-pose a first modular approach to NN design, wherein the NNis decomposed into a control module and several functionalmodules, implementing primitive operations. We illustratethe modular concept by comparing performances between amonolithic and a modular NN on a list sorting problem andshow the benefits in terms of training speed, training stabil-ity and maintainability. We also discuss some questions thatarise in modular NNs.
ISSN: 1613-0073
Source: CEUR Workshop Proceedings [ISSN 1613-0073], v. 2350, (Abril 2019)
Appears in Collections:Actas de congresos
Adobe PDF (13,46 MB)
Show full item record

Google ScholarTM



Export metadata

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