Title :
A Neural Network-Based Design Automation of a Second Generation Current Conveyor
Author :
Kahraman, Nihan ; Kiyan, T.
Author_Institution :
Electron. & Telecommun. Eng., Yildiz Tech. Univ. Istanbul, Istanbul, Turkey
Abstract :
An artificial neural network approach for the automated design of a positive type second generation current conveyor is presented in this paper. A multi-layer perceptron structure is successfully employed to estimate the corresponding transistor dimensions for a given set of desired performance criteria of the circuit. Data generated by a circuit simulation program (SPICE) is used to train the artificial neural network. The excellent agreement between the desired specifications and the actual results from SPICE simulation results approves that neural networks are powerful tools for automated analog circuit sizing.
Keywords :
SPICE; analogue circuits; circuit simulation; current conveyors; electronic design automation; multilayer perceptrons; performance evaluation; transistor circuits; SPICE simulation; artificial neural network approach; automated analog circuit sizing; circuit performance criteria; circuit simulation program; multilayer perceptron structure; neural network-based design automation; positive type second generation current conveyor; transistor dimensions; Artificial neural networks; Bandwidth; Design automation; Optimization; SPICE; Simulation; Transistors; Computer aided design (CAD); multilayer perceptron (MLP); neural networks; positive second generation current conveyor (CCII+);
Conference_Titel :
Computational Science and Computational Intelligence (CSCI), 2014 International Conference on
Conference_Location :
Las Vegas, NV
DOI :
10.1109/CSCI.2014.150
