Pregled bibliografske jedinice broj: 443778
Accelerated Gradient Learning Algorithm for Neural Network Weights Update
Accelerated Gradient Learning Algorithm for Neural Network Weights Update // Knowledge-Based Intelligent Information and Engineering Systems / Lovrek, Ignac ; Howlett, Robert J. ; Jain, Lakhmi C. (ur.).
Berlin : Heidelberg: Springer, 2009. str. 49-56
CROSBI ID: 443778 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Accelerated Gradient Learning Algorithm for Neural Network Weights Update
Autori
Hocenski, Željko ; Antunović, Mladen ; Filko, Damir
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
Knowledge-Based Intelligent Information and Engineering Systems
Urednik/ci
Lovrek, Ignac ; Howlett, Robert J. ; Jain, Lakhmi C.
Izdavač
Springer
Grad
Berlin : Heidelberg
Godina
2009
Raspon stranica
49-56
ISBN
978-3-540-85562-0
Ključne riječi
time critical processes, algorithm decomposition, neural network, weights update, gradient learning method, parallel processing
Sažetak
This work proposes decomposition of gradient learning algorithm for neural network weights update. 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 in multiple thread execution.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
165-0361621-2000 - Distribuirano računalno upravljanje u transportu i industrijskim pogonima (Hocenski, Željko, MZO ) ( CroRIS)
165-0362980-2002 - Postupci raspoređivanja u samoodrživim raspodijeljenim računalnim sustavima (Martinović, Goran, MZO ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek
