作者: Fikret Başar Gencer , Xhesila Xhafa , Benan Beril İnam , Mustafa Berke Yelten
DOI: 10.1007/S10470-020-01713-X
关键词:
摘要: This paper focuses on the design and validation of an analog artificial neural network. Basic building blocks ANN have been constructed in UMC 90 nm device technology. Performance metrics demonstrated through circuit simulations. The weights estimated automated back-propagation algorithm, which is running simulations during weight optimization. Two case studies, operation XOR logic gate a full adder captured using proposed ANN. Monte Carlo analysis reveals that operates with accuracy 99.85%.