Abstract
As proposed by L.O.Chua and L.Yang in [1], if we discretize the time in the equations that describe a Cellular Neural Network (CNN), we obtain a difference equation that recalls the dynamics of cellular automata. In this paper a hardware accelerator for CNN's with the structure of a cellular automaton is proposed. Its simple architecture allows the implementation of large arrays with high efficiency.
Preview
Unable to display preview. Download preview PDF.
References
Chua, L.O. and Yang. L. Cellular Neural Networs: Theory. Trans. on Circuits and Systems, 35 (1988), pp. 1257–1272.
Chua, L.O. and Yang, L. Cellular Neural Networs: Applications. Trans. on Circuits and Systems, 35 (1988), pp. 1273–1290.
Yang, L., Chua, L.O. and Krieg, K.R. VLSI Implementation of Cellular Neural Networks. Proc. Int. Symp. on Circuits and Systems, IEEE, 1990, pp. 2425–2427.
Roska, T. A Hardware accelerator board for cellular neural networks: CNN-HAC. Proc. First Cellular Neural Networks & Applications International Workshop. IEEE, 1990, pp. 160–168.
Harrer, H., Nossek, J.A. and Stelzl, R. An Analog Implementation of Discrete-Time Cellular Neural Networks. Trans. on Neural Networks, 3, (1992), pp. 466–477.
Vittoz, E. Analog VLSI Implementation of Neural Networks. Proc. Int. Symp. on Circuits and Systems, IEEE, 1990, pp. 2524–2527.
Rodrígnez Vázquez, A., Domínguez-Castro, R. and Huertas, J.L. Accurate Design of Analog CNN in CMOS Digital Technologies. Proc. First Cellular Neural Networks & Applications International Workshop, IEEE, 1990, pp. 273–280.
Preston, K. and Duff, M.J.B. Modern Cellular Automata. Theory and Applications. Plenum Press, N.Y., 1984.
Toffoli, T. and Margolus, N. Cellular Automata Machines. MIT Press, Cambridge, Massachussets, 1987.
Forrest, B.M., Roweth D., Stroud N., Wallace, D.J., and Wilson, G.V. Implementing neural network models on parallel computers. Comput. J. 30 (1987), pp. 413–419.
Pomerleau, D.A., Gsciora, G.S., Touretzky, D.S., and Kung, H.T. Neural network simulation at warp speed: How we get 17 million connections per second. Proc. Int. Conf. on Neural Networks, IEEE, July 1988, Vol. II, pp. 143–150.
Kung, S.Y., and Hwang, J.N. A unified systolic architecture for artifical neural nets. Proc. Int. Conf. on Systolic Arrays, IEEE, 1988, pp. 163–174.
Ghosh, J., and Hwang, K. Mapping neural networks onto message-passing multicomputers. J. Parallel Distrib. Comput. 6, (1989), 221–230.
Lin, W.M., Prasanna Kumar, V.K., and Wojtek Przytula, K. Algorithmic mapping of neural network models onto parallel SIMD machines. Trans. Comput., 40, (Dec. 1991), pp. 1390–1401.
James, Mark, and Hoang, D. Design of low-cost, real-time simulation systems for large neural networks. J. Parallel Distrib. Comput., 14, 221–235.
Chu, L.-C., and Wah, B.W. Optimal mapping of neural-network learning on message-passing multicomputers. J. Parallel Distrib. Comput., 14, 319–339.
Moldovan, D.I.M. and Fortes, J.A.B. Partitioning and mapping of algorithms into fixed size systolic arrays. Trans. on Comput., 35 (1986), pp. 1–12.
Kung. S.Y. VLSI Processor Arrays. Prentice-Hall, Englewood-Cliffs, N.J., 1987.
Lougheed, R.M. and McCubbrey, D.L. The Cytocomputer: A practical pipelined image processor, in: Proc. 7th. Ann. Int. Symp. on Computer Architecture, 1980, pp. 271–277.
INMOS. The transputer family 1987. 1987.
Nordström, T. and Svensson, B. Using and Designing Massively Parallel Computers for Artificial Neural Networks”. J. Parallel Distrib. Comput.. 14, pp. 260–285.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Torralba, A. (1995). Low-cost accelerator for the simulation of Cellular Neural Networks. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_239
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_239
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive