DocumentCode :
2773014
Title :
Optimization of Binary-Output CNNs: First Step of an Analytical Design Process
Author :
Benedic, Y. ; Mercklé, Jean
Author_Institution :
Haute-Alsace Univ., Mulhouse
fYear :
0
fDate :
0-0 0
Firstpage :
2800
Lastpage :
2806
Abstract :
A binary-output cellular neural network implements a threshold-logic function. It maps every input-vector to one vertice of a hypercube and uses a hyperplane to determine its class. The task achieved by a given cellular neural network is considered non-optimal if the hyperplane is poorly positioned in the hypercube, being unnecessarily close to one of its vertices. This property is crucial since cellular neural networks deal with analog signals, meaning that even binary values (namely, the inputs and the initial internal states) will slightly vary about their mean value. This paper presents an algorithm which partially solves this optimization problem. It is based on an original Boolean representation of the threshold-logic function achieved by a cellular neural network. By analyzing its functional symmetries, this algorithm tweaks the original hyperplane to make it fit them. It results in an improved implementation of the threshold-logic function. This algorithm turns out to be the first step of an analytical design method, capable of computing the best hyperplane position, out of a non-optimal one.
Keywords :
cellular neural nets; optimisation; threshold logic; analog signals; binary-output cellular neural network; optimization problem; original Boolean representation; threshold-logic function; Algorithm design and analysis; Cellular neural networks; Design methodology; Design optimization; Hypercubes; Lattices; Nearest neighbor searches; Neurofeedback; Neurons; Process design;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2006. IJCNN '06. International Joint Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-9490-9
Type :
conf
DOI :
10.1109/IJCNN.2006.247187
Filename :
1716477
Link To Document :
بازگشت