Napredna pretraga

Pregled bibliografske jedinice broj: 443778

Accelerated Gradient Learning Algorithm for Neural Network Weights Update


Hocenski, Željko; Antunović, Mladen; Filko, Damir
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


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


Projekt / tema
165-0361621-2000 - Distribuirano računalno upravljanje u transportu i industrijskim pogonima (Željko Hocenski, )
165-0362980-2002 - Postupci raspoređivanja u samoodrživim raspodijeljenim računalnim sustavima (Goran Martinović, )

Ustanove
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek