Abstract
The three-dimensional (3D) model of a feedforward neural network(NN) based on so called N-hypercube topology isproposed. The N-hypercube is different from theclassical hypercube used in communication theory, and in Booleanalgebra. This new structure has been created based on a novelalgorithm for embedding a binary decision tree and binary decisiondiagram into a N-hypercube. It is shown thatN-hypercube topology is a reasonable solution toimplement NN of threshold gates, in particular, on thesingle-electron devices. The 3D design methodology of feedforwardNN is oriented to technology mapping to nanodevices. Results ofextensive experimental study of feedforward networks consistingof over 3500 N-hypercubes are presented.
Similar content being viewed by others
References
Asahi, N., Akazawa, M. & Amemiya, Y. (1997). Single-Electron Logic Device Based on the Binary Decision Diagram. IEEE Transactions on Electron Devices 44(7): 1109–1116.
Bryant, R. E. & Meinel, C. (2002). Ordered Binary Decision Diagrams: Foundations, Applications and Innovations. In Hassoun, S. & Sasao, T. (eds.), Logic Synthesis and Verification, 285–307. Kluwer Academic Publishers.
Fiesler, E. & Beale, R. (eds.) (1997). Handbook on Neural Computation. IOP Publishing Ltd and Oxford University Press.
Frank, M. P. & Knight, T. F., Jr. (1998). Ultimate Theoretical Models of Nanocomputers. Nanotechnology (9): 162–176.
Likharev, K. (1999). Single – Electron Devices and Their Applications. Proceedings of IEEE 87(4): 606–632.
Okabe, A., Boots, B. & Sugihara, K. (1992). Spatial Tessellations. Concept and Applications of Voronoi Diagrams. John Wiley & Sons.
Roth, J. P. (1999). Mathematical Design: Building Reliable Complex Computer Systems. IEEE Press.
Siu, K-Y., Roychowdhury, V. P. & Kailath, T. (1991). Depth-Size Tradeoffs for Neural Computation. IEEE Transactions on Computers C-40(12): 1402–1411.
Saad, Y. & Schultz, M. H. (1988). Topological Properties of Hypercubes. IEEE Transactions on Computers. 37(7): 867–872.
Takahashi, Y., Fujiwara, A., Ono, Y. & Murase, K. (2000). Silicon Single-Electron Devices and Their Applications. In Proceedings of 30th IEEE International Symposium on Multiple-Valued Logic, 411–420.
Öhring, S. & Das, S. K. (1999). Incomplete Hypercubes: Embeddings of Tree-Related Networks. Journal of Parallel and Distributed Computing (26): 36–47.
Yamada, T., Kinoshita, Y., Kasai, S., Hasegawa, H. & Amemiya, Y. (2001). Quantum – Dot Logic Circuits Based on Shared Binary – Decision Diagram. Journal Applied Phys., Japan 40(7), Part 1: 4485–4488.
Yanushkevich, S., Shmerko, V., Malyugin, V. & Dziurzanski, P. (2002). Linarity of Word-Level Models: New Understanding. In Proceedings of IEEE/ACM 11th International Workshop on Logic and Synthesis, 67–72. New Orleans.
Yanushkevich, S., Shmerko, V. & Dziurzanski, P. (2004). Logic Circuit Representation by Linear Decision Diagrams with Extention to Nanosructures. Automation and Remote Control. Special Issue on Arithmetical Logic in Control Systems. Plenum Academic Publishers, in press.
Wasshuber, C. (2001). Computational Single-Electronics. Springer Verlag.
Webster, J. (ed.) (1999). Encyclopedia of Electrical and Electronics Engineering. John Willey & Sons.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Shmerko, V.P., Yanushkevich, S.N. Three-Dimensional Feedforward Neural Networks and Their Realization by Nano-Devices. Artificial Intelligence Review 20, 473–494 (2003). https://doi.org/10.1023/B:AIRE.0000006611.32608.f2
Issue Date:
DOI: https://doi.org/10.1023/B:AIRE.0000006611.32608.f2