Abstract
This paper presents an architecture for the implementation of a large Stochastic Hopfield Neural Networks (SHNNs). The sequential SHNN, originally proposed in [1], takes a long time to convergence. On the other hand, the connection between chips limits to one hundred the number of neurons of the fully parallel SHNN proposed in [2]–[3]. A multichip approach proposed in this paper overcome both problems. The architecture, using a mixed parallel-sequential strategy, reduces the number of interconection lines to k while accelerates the convergence time of the network in [1] by a factor k. A partitioning problem is simulated to evaluate the behavior of the network.
Preview
Unable to display preview. Download preview PDF.
References
D.E. van den Bout and T.K.Miller III, “A digital architecture employing stochasticism for the simulation of Hopfield neural nets”. IEEE Trans. Circuits and Systems, vol. 36, pp. 732–738, May 1989.
A.Torralba, F.Colodro. “Towards a fully parallel Stochastic Hopfield Neural Network”. Proc. of the ISCAS'93, pp. 2741–2743, May 1993.
A.Torralba, F.Colodro. “Two digital circuits for a Fully Parallel Stochastic Neural Network”. IEEE. Trans. of Neural Network (to appear)
D.E. van den Bout and T.K.Miller III, “TInMANN: The Integer Markovian Artificial Neural Network”.
M.S.Melton, T.Phan, D.S.Reeves, D.E. van den Bout, “The TInMANN VLSI chip”. IEEE Trans. Neural Networks, vol.3, no. 3, May 1992.
Y.Kondo and Y.Sawada, “Functional abilities of a stochastic logic neural network”. IEEE Trans. Neural Networks, vol. 3, no. 3, May 1992.
C.Janer and J.M.Quero, “Fully parallel summation in a new Stochastic Neural Network architecture”. IEEE Trans. Int. Conf. in Neural Network, San Francisco, 1993.
L.Dadda. “Some schemes for parallel multipliers”. Alta Freq., vol. 19, pp. 349–356, May 1965.
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., Colodro, F., Franquelo, L.G. (1995). A mixed parallel-sequential SHNN for large 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_251
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_251
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