Mostrar el registro sencillo del ítem

dc.contributor.authorCarrascosa, C.
dc.contributor.authorEnguix, F.
dc.contributor.authorRebollo, M.
dc.contributor.authorRincon, J.
dc.date2023-09
dc.date.accessioned2023-09-06T07:34:30Z
dc.date.available2023-09-06T07:34:30Z
dc.identifier.issn1989-1660
dc.identifier.urihttps://reunir.unir.net/handle/123456789/15214
dc.description.abstractOne of the main advancements in distributed learning may be the idea behind Google’s Federated Learning (FL) algorithm. It trains copies of artificial neural networks (ANN) in a distributed way and recombines the weights and biases obtained in a central server. Each unit maintains the privacy of the information since the training datasets are not shared. This idea perfectly fits a Multi-Agent System, where the units learning and sharing the model are agents. FL is a centralized approach, where a server is in charge of receiving, averaging and distributing back the models to the different units making the learning process. In this work, we propose a truly distributed learning process where all the agents have the same role in the system. We suggest using a consensus-based learning algorithm that we call Co-Learning. This process uses a consensus process to share the ANN models each agent learns using its private data and calculates the aggregated model. Co-Learning, as a consensus-based algorithm, calculates the average of the ANN models shared by the agents with their local neighbors. This iterative process converges to the averaged ANN model as a central server does. Apart from the definition of the Co-Learning algorithm, the paper presents its integration in SPADE agents, along with a framework called FIVE allowing to develop Intelligent Virtual Environments for SPADE agents. This framework has been used to test the execution of SPADE agents using Co-Learning algorithm in a simulation of an orange orchard field.es_ES
dc.language.isoenges_ES
dc.publisherInternational Journal of Interactive Multimedia and Artificial Intelligencees_ES
dc.relation.ispartofseries;vol. 8, nº 3
dc.relation.urihttps://www.ijimai.org/journal/sites/default/files/2023-08/ijimai8_3_2.pdfes_ES
dc.rightsopenAccesses_ES
dc.subjectcomplex networkses_ES
dc.subjectdistributed AIes_ES
dc.subjectmulti-agent systemses_ES
dc.subjectneural networkes_ES
dc.subjectIJIMAIes_ES
dc.titleConsensus-Based Learning for MAS: Definition, Implementation and Integration in IVEses_ES
dc.typearticlees_ES
reunir.tag~IJIMAIes_ES
dc.identifier.doihttps://doi.org/10.9781/ijimai.2023.08.004


Ficheros en el ítem

Thumbnail

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem