Browsing by Author "Bilgili, Erdem"
Now showing items 1-8 of 8
-
Applications of CNN with trapezoidal activation function
Bilgili, Erdem; Göknar, İzzet Cem; Uçan, Osman Nuri (Springer, 2006-01)This paper presents some applications of cellular neural network (CNN) scheme employing a new nonlinear activation function, called trapezoidal activation function (TAF). The new CNN structure can classify linearly ... -
Cellular neural network with trapezoidal activation function
Bilgili, Erdem; Göknar, İzzet Cem; Uçan, Osman Nuri (John Wiley & Sons, 2005-09)This paper presents a cellular neural network (CNN) scheme employing a new non-linear activation function, called trapezoidal activation function (TAF). The new CNN structure can classify linearly non-separable data points ... -
Design and development of material and information flow for supply chains using genetic cellular networks
Ziarati, Martin; Stockton, David; Uçan, Osman Nuri; Bilgili, Erdem (Doğuş Üniversitesi, 2002-01-15)In a recent paper by authors (Ziarati and Ucan, January 2001) a Back Propagation-Artificial Neural Network (BP-ANN) was adapted for predicting the required car parts quantities in a real and major auto parts supplier chain. ... -
Geriye yayılma algoritması kullanılarak yaprak desenlerinin sınıflandırılması
Bilgili, Erdem; Uçan, Osman Nuri (Doğuş Üniversitesi, 2001-07-15)Bu çalışmada beş farklı bitki yaprağı kullanılarak, çok katmanlı yapay sinir ağı geriye yayılma algoritması ile eğitilmiştir. Eğitim işleminden sonra yapay sinir ağına tanıtılan her bir yaprak türünden 15 adet yaprak ... -
Localisation of archeological sites using multi-level cellular neural networks
Göknar, İzzet Cem; Bilgili, Erdem; Uçan, Osman Nuri; Albora, Ali Muhittin (International Institute of Informatics and Systemics, 2002-07-14)In this paper, a supervised algorithm, Mufti-Level Cellular Neural Network (ML-CNN) is introduced, developed and then applied to archeological ruins of the Hittite Empire in Turkey. ML-CNN is a stochastic image processing ... -
Potential anomaly separation and archeological site localization using genetically trained multi-level cellular neural networks
Bilgili, Erdem; Göknar, İzzet Cem; Albora, Ali Muhittin; Uçan, Osman Nuri (Electronics and Telecommunications Research Institute (ETRI), 2005-06)In this paper, a supervised algorithm for the evaluation of geophysical sites using a multi-level cellular neural network (ML-CNN) is introduced, developed, and applied to real data. ML-CNN is a stochastic image processing ... -
Potential anomaly separation using genetically trained multi-level cellular neural networks
Bilgili, Erdem; Uçan, Osman Nuri; Albora, Ali Muhittin; Göknar, İzzet Cem (IEEE, 2002-07-22)In this paper, multi-level genetic cellular neural networks (ML-GCNN) are applied to the geophysical problem of potential anomaly separation and satisfactory results are obtained, compared to classical deterministic ... -
Stability of CNN with trapezoidal activation function
Bilgili, Erdem; Göknar, İzzet Cem; Uçan, Osman Nuri; Albora, Ali Muhittin (Springer, 2005-09)This paper presents the stability conditions of cellular neural network (CNN) scheme employing a new nonlinear activation function, called trapezoidal activation function (TAF). The new CNN structure can classify linearly ...
