Pretraga

Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 366243

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 / Ignac Lovrek and Robert J. Howlett and Lakhmi C. Jain (ur.).
Heidelberg: Springer, 2008. str. 49-56 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)

CROSBI ID: 366243 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
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Knowledge-Based Intelligent Information and Engineering Systems / Ignac Lovrek and Robert J. Howlett and Lakhmi C. Jain - Heidelberg : Springer, 2008, 49-56

ISBN
978-3-540-85562-0

Skup
Knowledge-Based Intelligent Information and Engineering Systems, KES 2008

Mjesto i datum
Zagreb, Hrvatska, 03.09.2008. - 05.09.2008

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

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
Elektrotehnika, Računarstvo



POVEZANOST RADA

Projekti:
165-0361621-2000 - Distribuirano računalno upravljanje u transportu i industrijskim pogonima (Hocenski, Željko, MZO ) ( CroRIS)

Ustanove:
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek

Profili:

Avatar Url Željko Hocenski (autor)

Avatar Url Mladen Antunović (autor)

Avatar Url Damir Filko (autor)

Citiraj ovu publikaciju:

Hocenski, Željko; Antunović, Mladen; Filko, Damir
Accelerated Gradient Learning Algorithm for Neural Network Weights Update // Knowledge-Based Intelligent Information and Engineering Systems / Ignac Lovrek and Robert J. Howlett and Lakhmi C. Jain (ur.).
Heidelberg: Springer, 2008. str. 49-56 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Hocenski, Ž., Antunović, M. & Filko, D. (2008) Accelerated Gradient Learning Algorithm for Neural Network Weights Update. U: Ignac Lovrek and Robert J. Howlett and Lakhmi C. Jain (ur.)Knowledge-Based Intelligent Information and Engineering Systems.
@article{article, author = {Hocenski, \v{Z}eljko and Antunovi\'{c}, Mladen and Filko, Damir}, year = {2008}, pages = {49-56}, keywords = {time critical processes, algorithm decomposition, neural network, weights update, gradient learning method, parallel processing}, isbn = {978-3-540-85562-0}, title = {Accelerated Gradient Learning Algorithm for Neural Network Weights Update}, keyword = {time critical processes, algorithm decomposition, neural network, weights update, gradient learning method, parallel processing}, publisher = {Springer}, publisherplace = {Zagreb, Hrvatska} }
@article{article, author = {Hocenski, \v{Z}eljko and Antunovi\'{c}, Mladen and Filko, Damir}, year = {2008}, pages = {49-56}, keywords = {time critical processes, algorithm decomposition, neural network, weights update, gradient learning method, parallel processing}, isbn = {978-3-540-85562-0}, title = {Accelerated Gradient Learning Algorithm for Neural Network Weights Update}, keyword = {time critical processes, algorithm decomposition, neural network, weights update, gradient learning method, parallel processing}, publisher = {Springer}, publisherplace = {Zagreb, Hrvatska} }

Podijeli:





Contrast
Increase Font
Decrease Font
Dyslexic Font
CROSBI koristi kolačiće (cookies) kako bi poboljšao funkcionalnost stranice.