Non-uniform cellular finite automata neural networks

Download

035450.pdf

Date

1994

Author

Bakırkaya, Sedat

Metadata

Show full item record

Item Usage Stats

89
views

0
downloads

URI

https://hdl.handle.net/11511/11654

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Non-uniform cellular automata with gaussian potential function units Yıldırım, Dursun Gökhan; Güler, Marifi; Department of Computer Engineering (1994)
Non-uniform cellular automata networks having capability of classification and computation. Kılıç, Hürevren; Department of Computer Engineering (1992)
Non-Abelian gauge theories of the Yang-Mills type Abuhatab, Ahmed; Başkal, Sibel; Department of Physics (2003) In this thesis, starting from the effective Lagrangians of the standard Yang-Mills, higher derivative Yang-Mills and the Chern-Simons- Yang-Mills theories, we have given the corresponding field equations and the symmetric gauge invariant energy- momentum tensors. Lagrangians containing higher derivative terms have been found useful for discussing the long lange effects of the gluon fields. A numeri cal solution is found for a spherically symmetric static gauge potential. On the other hand, Chern-Simons- Yan...
Non-normal bivariate distributions: estimation and hypothesis testing Qunsiyeh, Sahar Botros; Tiku, Moti Lal; Department of Statistics (2007) When using data for estimating the parameters in a bivariate distribution, the tradition is to assume that data comes from a bivariate normal distribution. If the distribution is not bivariate normal, which often is the case, the maximum likelihood (ML) estimators are intractable and the least square (LS) estimators are inefficient. Here, we consider two independent sets of bivariate data which come from non-normal populations. We consider two distinctive distributions: the marginal and the conditional dist...
NON-EUCLIDEAN VECTOR PRODUCT FOR NEURAL NETWORKS Afrasiyabi, Arman; Badawi, Diaa; Nasır, Barış; Yildiz, Ozan; Yarman Vural, Fatoş Tunay; ÇETİN, AHMET ENİS (2018-04-20) We present a non-Euclidean vector product for artificial neural networks. The vector product operator does not require any multiplications while providing correlation information between two vectors. Ordinary neurons require inner product of two vectors. We propose a class of neural networks with the universal approximation property over the space of Lebesgue integrable functions based on the proposed non-Euclidean vector product. In this new network, the "product" of two real numbers is defined as the sum ...

Citation Formats

S. Bakırkaya, “Non-uniform cellular finite automata neural networks,” Middle East Technical University, 1994.