|Title:||Modularity as a means for complexity management in neural networks learning||Authors:||Castillo Bolado, David Alejandro
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.||URI:||http://hdl.handle.net/10553/56249||ISSN:||1613-0073||Source:||CEUR Workshop Proceedings [ISSN 1613-0073], v. 2350, (Abril 2019)|
|Appears in Collections:||Actas de congresos|
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.