Pretraga

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

Napredna pretraga

Pregled bibliografske jedinice broj: 5780

Recurrent neural network synthesis using interaction activation functions

Novaković, Branko
Recurrent neural network synthesis using interaction activation functions // Proceedings of the 1996 IEEE International Conference on Robotics and Automation, Vol. 2 / Norman Caplan (ur.).
Minneapolis (MN): IEEE, The Institute of Electrical and Electronics Engineers, USA, 1996. str. 1608-1613 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)

CROSBI ID: 5780 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Recurrent neural network synthesis using interaction activation functions

Autori
Novaković, Branko

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

Izvornik
Proceedings of the 1996 IEEE International Conference on Robotics and Automation, Vol. 2 / Norman Caplan - Minneapolis (MN) : IEEE, The Institute of Electrical and Electronics Engineers, USA, 1996, 1608-1613

Skup
The 1996 IEEE International Conference on Robotics and Automation

Mjesto i datum
Minneapolis (MN), Sjedinjene Američke Države, 22.04.1996. - 28.04.1996

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Recurrent neural networks; interaction activation functions; one-step learning

Sažetak
Abstract - A new very fast algorithm for synthesis of recurrent discrete-time neural networks (NN) is proposed. For this purpose the following concepts are employed: (i) introduction of interaction activation functions, (ii) time-varying NN weights distribution, (iii) time-discrete domain synthesis and (iiii) one-step learning iteration approach.. The proposed NN synthesis procedure is useful for applications to identification and control of nonlinear, very fast, dynamical systems. In this sense a recurrent NN for a nonlinear robot control is designed.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo



POVEZANOST RADA

Projekti:
120009

Ustanove:
Fakultet strojarstva i brodogradnje, Zagreb

Profili:

Avatar Url Branko Novaković (autor)

Citiraj ovu publikaciju:

Novaković, Branko
Recurrent neural network synthesis using interaction activation functions // Proceedings of the 1996 IEEE International Conference on Robotics and Automation, Vol. 2 / Norman Caplan (ur.).
Minneapolis (MN): IEEE, The Institute of Electrical and Electronics Engineers, USA, 1996. str. 1608-1613 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Novaković, B. (1996) Recurrent neural network synthesis using interaction activation functions. U: Norman Caplan (ur.)Proceedings of the 1996 IEEE International Conference on Robotics and Automation, Vol. 2.
@article{article, author = {Novakovi\'{c}, Branko}, year = {1996}, pages = {1608-1613}, keywords = {Recurrent neural networks, interaction activation functions, one-step learning}, title = {Recurrent neural network synthesis using interaction activation functions}, keyword = {Recurrent neural networks, interaction activation functions, one-step learning}, publisher = {IEEE, The Institute of Electrical and Electronics Engineers, USA}, publisherplace = {Minneapolis (MN), Sjedinjene Ameri\v{c}ke Dr\v{z}ave} }
@article{article, author = {Novakovi\'{c}, Branko}, year = {1996}, pages = {1608-1613}, keywords = {Recurrent neural networks, interaction activation functions, one-step learning}, title = {Recurrent neural network synthesis using interaction activation functions}, keyword = {Recurrent neural networks, interaction activation functions, one-step learning}, publisher = {IEEE, The Institute of Electrical and Electronics Engineers, USA}, publisherplace = {Minneapolis (MN), Sjedinjene Ameri\v{c}ke Dr\v{z}ave} }

Podijeli:





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