Accelerated gradient learning algorithm for neural network weights update (CROSBI ID 162234)
Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija
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