crta
Hrvatska znanstvena Sekcija img
bibliografija
3 gif
 Naslovna
 O projektu
 FAQ
 Kontakt
4 gif
Pregledavanje radova
Jednostavno pretraživanje
Napredno pretraživanje
Skupni podaci
Upis novih radova
Upute
Ispravci prijavljenih radova
Ostale bibliografije
Slični projekti
 Bibliografske baze podataka

Pregled bibliografske jedinice broj: 443778

Poglavlje/Rad u knjizi

Autori: Hocenski, Željko; Antunović, Mladen; Filko, Damir
Naslov: Accelerated Gradient Learning Algorithm for Neural Network Weights Update
( Accelerated Gradient Learning Algorithm for Neural Network Weights Update )
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
Serija: Lecture Notes in Computer Science
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
( 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.
Projekt / tema: 165-0361621-2000, 165-0362980-2002
Izvorni jezik: eng
Kategorija: Znanstveni
Znanstvena područja:
Računarstvo
URL Internet adrese: http://www.springerlink.com/content/p76738nx613k327n/?p=0497446c1b6e4edbbf96ebe877255733&pi=1
Upisao u CROSBI: dfilko@etfos.hr (dfilko@etfos.hr), 9. Vel. 2010. u 16:09 sati



Verzija za printanje   za tiskati


upomoc
foot_4