A method for designing CNN templates

Author

Hernandez, J.A.M. ; Castaneda, F.G. ; Cadenas, José Antonio Moreno

Author_Institution

Inst. Politecnico Nacional, Mexico City

fYear

2007

Firstpage

153

Lastpage

156

Abstract

Cellular neural networks (CNN) are very useful for image processing tasks [1],[2]. One problem with CNN networks is the lack of a programming method to realize a processing task. The cloning templates entirely specifies the programming of a CNN net. There are a lot of cloning templates for several tasks [3]-[4], got by mathematical analysis or heuristically [4]-[9]. However for some specific tasks is very difficult to find the correct templates. In this paper a procedure for finding cloning templates for image processing tasks is described, using a gradient method. A set of CNN templates obtained using the proposed procedure is shown.

Keywords

cellular neural nets; gradient methods; image processing; learning (artificial intelligence); stochastic processes; CNN template design; cellular neural network; cloning template; image processing; learning; stochastic gradient descent method; Cellular neural networks; Cloning; Design engineering; Design methodology; Equations; Image processing; Mathematics; Physics; Pixel; Stochastic processes; CNN network; learning rules; stochastic gradient descent method; training set;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Electronics Engineering, 2007. ICEEE 2007. 4th International Conference on

Conference_Location

Mexico City

Print_ISBN

978-1-4244-1166-5

Electronic_ISBN

978-1-4244-1166-5

Type

conf

DOI

10.1109/ICEEE.2007.4344996

Filename

4344996