Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi

Accelerated gradient learning algorithm for neural network weights update (CROSBI ID 162234)

Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija

Hocenski, Željko ; Antunović, Mladen ; Filko, Damir Accelerated gradient learning algorithm for neural network weights update // Neural computing and applications, 19 (2010), 2; 219-225. doi: 10.1007/s00521-009-0286-7

Podaci o odgovornosti

Hocenski, Željko ; Antunović, Mladen ; Filko, Damir

engleski

Accelerated gradient learning algorithm for neural network weights update

This work proposes decomposition of square approximation algorithm for neural network weights update. Suggested improvement results in alternative method that converge in less iteration and is inherently parallel. Decomposition enables parallel execution convenient for implementation on computer grid. Improvements are reflected in accelerated learning rate which may be essential for time critical decision processes. Proposed solution is tested and verified on MLP neural network case study, varying a wide range of parameters, such as number of inputs/outputs, length of input/output data, number of neurons and layers. Experimental results show time savings up to 40% in multiple thread execution.

neural network; weights update; gradient learning method; parallel processing.

Special Issue - KES2008 ; Rad je kao predavanje prezentiran na skupu 12th International Conference Knowledge-Based Intelligent Information and Engineering System (KES 2008), održanom od 03.-05.09.2008., Zagreb, Hrvatska ; u cjelosti je uz međunarodnu recenziju objavljen u Proceedings, Part I. ; Ignac Lovrek, Robert J. Howlett, Lakhmi C. Jain (ur.) ; Lecture Notes in Computer Science. Vol. 5177 ; Berlin : Springer, 2008. ; ISBN 978-3-540-85562-0 ; str. 49-56.

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o izdanju

19 (2)

2010.

219-225

objavljeno

0941-0643

10.1007/s00521-009-0286-7

Povezanost rada

Elektrotehnika, Računarstvo

Poveznice
Indeksiranost