In this paper, we propose a scalable, decentralized learning algorithm for Random Weights Fuzzy Neural Networks, when training data is distributed through a network of interconnected computing agents. In this scenario, the aim is for all the agents to converge to a single model, with the requirement that only local communications between the agents are permitted. In this work we assume that all the agents know the parameters of the antecedents, while the parameters of the consequents are estimated by using the Alternating Direction Method of Multipliers strategy. Experimental results show that the performance of the proposed algorithm is comparable to that of a centralized model, where all the data is collected by a single agent before the training process. To this date, this is the first publication that addressed the problem of training a fuzzy neural network over a fully decentralized infrastructure.
Distributed learning of random weights fuzzy neural networks / Fierimonte, Roberto; Barbato, Marco; Rosato, Antonello; Panella, Massimo. - STAMPA. - (2016), pp. 2287-2294. (Intervento presentato al convegno IEEE International Conference on Fuzzy Systems tenutosi a Vancouver, Canada nel 24-29 luglio 2016) [10.1109/FUZZ-IEEE.2016.7737978].
Distributed learning of random weights fuzzy neural networks
ROSATO, ANTONELLO;PANELLA, Massimo
2016
Abstract
In this paper, we propose a scalable, decentralized learning algorithm for Random Weights Fuzzy Neural Networks, when training data is distributed through a network of interconnected computing agents. In this scenario, the aim is for all the agents to converge to a single model, with the requirement that only local communications between the agents are permitted. In this work we assume that all the agents know the parameters of the antecedents, while the parameters of the consequents are estimated by using the Alternating Direction Method of Multipliers strategy. Experimental results show that the performance of the proposed algorithm is comparable to that of a centralized model, where all the data is collected by a single agent before the training process. To this date, this is the first publication that addressed the problem of training a fuzzy neural network over a fully decentralized infrastructure.File | Dimensione | Formato | |
---|---|---|---|
Fierimonte_Distributed_2016.pdf
solo utenti autorizzati
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
205.9 kB
Formato
Adobe PDF
|
205.9 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.