Naslov
Modelling of SCFL Circuits

Autori
Čeperić, Vladimir ; Barić, Adrijan

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

Izvornik
27th International Convention : conferences Microelectronics, Electronics and Electronics Technologies (MEET) and Hypermedia and Grid System (HGS) (MIPRO 2004) : proceedings / Biljanović, Petar ; Skala, Karolj - Rijeka : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2004, 89-93

Skup
International Conference on Microelectronics, Electronics and Electronic Technologies ; International Conference on Hypermedia and Grid System

Mjesto i datum
Opatija, Hrvatska, 24.05.2004. - 28.05.2004

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
artificial neural networks; modelling; SCFL

Sažetak
The use of artificial neural networks in modelling of electronic circuits is investigated. A method of modelling electronic circuits is presented in which an artificial neural network is used as universal approximator with and without a signal generator. A simple and effective way to obtain necessary data for learning the artificial neural network used in model is presented. These methods ensure a simple, fast and accurate modelling of the electronic circuits. The models yield good result for situations not specified in the learning data set because of the generalization property of artificial neural networks and the method used to obtain learning data. Both methods can be used for modelling based on measurements. The models of the GaAs SCFL circuits for circuit simulation software are developed.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika

POVEZANOST RADA