New Digital Architecture of CNN for Pattern Recognition

Raschman, Emil; Záluský, Roman; Ďuračková, Daniela

doi:10.2478/v10187-010-0031-6

Abstract

The paper deals with the design of a new digital CNN (Cellular Neural Network) architecture for pattern recognition. The main parameters of the new design were the area consumption of the chip and the speed of calculation in one iteration. The CNN was designed as a digital synchronous circuit. The largest area of the chip belongs to the multiplication unit. In the new architecture we replaced the parallel multiplication unit by a simple AND gate performing serial multiplication. The natural property of this method of multiplication is rounding. We verified some basic properties of the proposed CNN such as edge detection, filling of the edges and noise removing. At the end we compared the designed network with other two CNNs. The new architecture allows to save till 86% gates in comparison with CNN with parallel multipliers.

References

CHUA, L. O.—YANG, L.: Cellular Neural Network: Theory, IEEE Trans. Circuits Systems 35 (Oct 1988), 1257-1272.10.1109/31.7600
Search in Google Scholar
CHUA, L. O.—YANG, L.: Cellular Neural Network: Aplications, IEEE Trans. Circuits Systems 35 (Oct 1988), 1273-1290.10.1109/31.7601
Search in Google Scholar
HNGGI, M—MOSCHYTZ, G. S.: Cellular Neural Network: Analysis, Design and Optimalization, Kluwer Academic Publisher, Boston, 2000.
Search in Google Scholar
SORDO, M.: Introduction to Neural Networks in Healthcare, Open Clinical Knowledge Management for Medical Care, Oct 2002.
Search in Google Scholar
LARSEN, J.: Introduction to Artifical Neural Network, 1 st Edition, Section for Digital Signal Processing Department of Mathematical Modeling Technical University of Denmark, Nov 1999.
Search in Google Scholar
SEUNG, S.: Introduction to Neural Networks: Lecture 1, The Massachusetts Institute of Technology — The Seung Lab, Sep 2002.
Search in Google Scholar
KVASNIČKA, V.—BEŇUŠKOVÁ, Ľ—POSPÍCHAL, J.—FARKAŠ, I.—TIŇO, P.—KRáĽ, A.: Introduction to Theory of Neural Network, IRIS, 1997. (in Slovak)
Search in Google Scholar
JEON, J.: Fuzzy and Neural Network Models for Analyses of Piles, A dissertation submitted to the Graduate Faculty of North Carolina State University, Raleigh, North Carolina, Aug 2007.
Search in Google Scholar
RESTREPO, H. F.—HOFFMAN, R.—PEREZ-URIBE, A.—TEUSCHER, C.—SANCHEZ, E.: A Networked FPGA-Based Hardware Implementation of a Neural Network Application, In (K.L. Pocek and J.M. Arnold Proceedings of the IEEE Symposium on Field Programmable Custom Computing Machines, FCCM'00, eds.), pp. 337-338, Napa, California, USA, Apr 17-19, 2000. IEEE Computer Society, Los Alamitos, C, A.
Search in Google Scholar
MUTHURAMALINGAM, A.—HIMAVATHI, S.—SRINIVASAN, E.: Neural Network Implementation Using FPGA: Issues and Application, International Journal of Information Technology 4 No. 2 (2008).
Search in Google Scholar
BOUBAKER, M.—KHALIFA, K. B.—GIRAU, B.—DOGUI, M.—BEDOUI, M. H.: On-Line Arithmetic Based Reprogrammable Hardware Implementation of LVQ Neural Network for Alertness Classification, IJCSNS International Journal of Computer Science and Network Security 8 No. 3 (Mar 2008).
Search in Google Scholar
LARKIN, D.—KINANE, A.—MURESAN, V.—O'CONNOR, N.: An Efficient Hardware Architecture for a Neural Network Activation Function Generator, Lecture Notes in Computer Science, 2006.10.1007/11760191_192
Search in Google Scholar
RASCHMAN, E.—ĎURAČKOVÁ, D.: The Novel Digital Design of a Cell for Cellular Neural Network, Proceedings of the Electronic Devices and Systems, Brno, Sep 2008, pp. 322-325.
Search in Google Scholar

New Digital Architecture of CNN for Pattern Recognition

Abstract

Paradigm

My account