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

Napredna pretraga

Pregled bibliografske jedinice broj: 719443

GPU Implementation of the Feedforward Neural Network with Modified Levenberg-Marquardt Algorithm


Bacek Tomislav, Dubravko Majetić, Danko Brezak
GPU Implementation of the Feedforward Neural Network with Modified Levenberg-Marquardt Algorithm // 2014 International Joint Conference on Neural Networks (IJCNN)
Beijing: IEEE, 2014. str. 785-791 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
GPU Implementation of the Feedforward Neural Network with Modified Levenberg-Marquardt Algorithm

Autori
Bacek Tomislav, Dubravko Majetić, Danko Brezak

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
2014 International Joint Conference on Neural Networks (IJCNN) / - Beijing : IEEE, 2014, 785-791

ISBN
978-1-4799-6627-1

Skup
2014 International Joint Conference on Neural Networks (IJCNN)

Mjesto i datum
Beijing, China, 06-11.07.2014

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Feedforward Neural Network; Levenberg-Marquardt Algorithm

Sažetak
In this paper, an improved Levenberg-Marquardt based feedforward neural network, with variable weight decay, is suggested. Furthermore, parallel implementation of the network on graphics processing unit is presented. Parallelization of the network is achieved on two different levels. First level of parallelism is data set level, where parallelization is possible due to inherently parallel structure of the feedforward neural networks. Second level of parallelism is Jacobian computation level. Third level of parallelism, i.e. parallelization of optimization search steps, is not implemented due to the variable weight decay, which makes third level of parallelism redundant. Suggested weight decay variation enables the compromise between higher accuracy with oscillations on one side and stable, but slower convergence on the other. To improve learning speed and efficiency, modification of random weight initialization is included. Testing of proposed algorithm is performed on two real domain benchmark problems. The results obtained and presented in this paper show effectiveness of proposed algorithm implementation.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo



POVEZANOST RADA


Projekt / tema
120-1201842-3048 - Umjetna inteligencija u upravljanju složenim nelinearnim dinamičkim sustavima (Josip Kasać, )
120-1201948-1938 - Napredni obradni sustavi i procesi (Toma Udiljak, )
120-1201948-1945 - Inteligentno vođenje obradnih sustava (Dubravko Majetić, )

Ustanove
Fakultet strojarstva i brodogradnje, Zagreb

Citiraj ovu publikaciju

Bacek Tomislav, Dubravko Majetić, Danko Brezak
GPU Implementation of the Feedforward Neural Network with Modified Levenberg-Marquardt Algorithm // 2014 International Joint Conference on Neural Networks (IJCNN)
Beijing: IEEE, 2014. str. 785-791 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Bacek Tomislav, Dubravko Majetić, Danko Brezak (2014) GPU Implementation of the Feedforward Neural Network with Modified Levenberg-Marquardt Algorithm. U: 2014 International Joint Conference on Neural Networks (IJCNN).
@article{article, year = {2014}, pages = {785-791}, keywords = {Feedforward Neural Network, Levenberg-Marquardt Algorithm}, isbn = {978-1-4799-6627-1}, title = {GPU Implementation of the Feedforward Neural Network with Modified Levenberg-Marquardt Algorithm}, keyword = {Feedforward Neural Network, Levenberg-Marquardt Algorithm}, publisher = {IEEE}, publisherplace = {Beijing, China} }