Abstract
Artificial neural network architectures exhibit properties (associative memory, classification, generalization,…) which roughly approximate some of our elementary brain properties. Classical or parallel computer simulations have been, and still are, invaluable tools for investigating their behavior, but require more and more power, becoming increasingly costly. The regularity of most networks architecture make them good candidates for hardwiring, and even better, integration in silicon. In this case, it is also expected to take advantage of the intrinsic robustness of neural architectures, which could make acceptable some defective circuits which would otherwise be rejected by current standards. One can expect to gain orders of magnitude in overall efficiency when simulations are done on these specialized circuits. We shall quickly review some current developments in silicon, especially the digital 64 neurons feedback network with included learning circuitry that we develop in cooperation with the ESPCI group. We shall also give some information on a long term project of wafer-scale integration.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Bibliography
Hopfield, J. J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA, vol. 79, pp. 2554–2558, 1982
Ackley, D.H., Hinton, G.E. and Sejnowski, T.J.: A learning algorithm for Boltzmann machines. Cognitive Science, vol. 9, pp. 147–169, 1985
Sivilotti, M., Emerling, M. R., and Mead, C.: A novel associative memory implemented using collective computation. In: Proc. Chapel Hill Conf. on VLSI, pp. 329–342, Computer Science Press 1985
Moopenn, A., Langenbacher, H., Thakoor, A. P. and Khanna, S.K.: A programmable binary synaptic matrix chip for electronic neural networks. IEEE Conf. on Neural Information Processing Systems, Natural and Synthetic, Denver (USA), 1987. In: Neural Information Processing Systems, Natural and Synthetic, D.Z. Anderson, ed., American Institute of Physics, 1988
Schwartz, D. B., Howard, R. E., Denker, J. S., Epworth, R. W., Graf, H. P., Hubbard, W., Jackel, L. D., Straughn, B. and Tennant, D. M.: Dynamics of microfabricated electronic neural networks. Appl. Phys. Lett., vol. 50, pp. 1110–1112, 1987
Verleysen, M., Sirletti, B., Vandemeulenbroecke, A.M., Jespers, P.G.A.: Neural networks for high-storage content-adressable memory: VLSI circuit and learning algorithm. IEEE Journal of solid-state circuits, vol. 24, no. 3, pp. 562–569, 1989
Sage, J.P., Thompson, K. and Withers, R.S.: An artificial network integrated circuit based on MNOS/CCD principles. In: Neural networks for computing, J.S. Denker ed., American Institute of Physics, 1986
Rückert, U. and Goser, K.: VLSI design of associative networks. International Workshop on VLSI for artificial intelligence, Oxford (GB), July 1988. In: VLSI for artificial intelligence, J.G. Delgado-Frias and W. Moore eds., Kluwer Academic, 1989
Holler, M., Tam, S., Castro, H. and Benson, R.: An electrically trainable artificial neural network with 10240 “floating gate” synapses. Proceedings of International Joint Conference on Neural Networks, Washington D.C., June 1989
Schwartz, D. B. and Howard, R. E.: Analog VLSI for adaptive learning, Neural Networks for Computing, Snowbird, 1988 (unpublished).
Alspector, J., Allen, R. B., Hu, V. and Satyanarayana, S.: Stochastic learning networks and their electronic implementation. IEEE Conf. on Neural Information Processing Systems, Natural and Synthetic, Denver (USA), 1987. In: Neural Information Processing Systems, Natural and Synthetic, D.Z. Anderson, ed., American Institute of Physics, 1988
Tsividis, Y.P. and Anastassiou, D.: Switched capacitor neural network. Electronic Lett, vol. 23, pp. 958–959, 1987
Hopfield, J.J.: On the effectiveness of neural network hardware. Proceedings of the workshop “Hardware implementation of neuron nets and synapses”, San Diego (USA), P. Mueller ed, pp. 120–124, Janupy 1988
Blayo, F. and Hurat, P.: A systolic architecture dedicated to neural networks. nEuro’88 conference, Paris, June 1988. In: Neural networks, from models to applications, L. Personnaz and GJ. Dreyfus, eds., IDSET, 1989
Murray, A. F., Smith, V. W. and Butler, Z. F.: Bit-serial neural networks, IEEE Conf. on Neural Information Processing Systems, Natural and Synthetic, Denver (USA), 1987. In: Neural Infonfiation Processing Systems, Natural and Synthetic, D.Z. Anderson, ed., American Institute of Physics, 1988
Duranton, M., Gobert, J. and Mauduit, N.: A digital VLSI module for neural networks. nEuro’88 conference, Paris, June 1988. In: Neural networks, from models to applications. LJ. Personnaz and G. Dreyfus, eds., IDSET, 1989
Personnaz, L., Johannet, A., Dreyfus, G., Weinfeld, M.: Towards a neural network chip: a performance assessment and a simple example. nEuro’88 conference, Paris, June 1988. In: Neural networks, from models to applications, L. Personnaz and G. Dreyfus, eds., IDSET, 1989
Weinfeld, M.: A fully digital CMOS integrated Hopfield network including the learning algorithm. International Workshop on VLSI for artificial intelligence, Oxford (GB), July 1988. In: VLSI for artificial intelligence, J.G. Delgado-Frias and W. Moore eds., Kluwer Academic, 1989
Diederich, S. and Opper, M.: Learning of correlated patterns in spin-glass networks by local learning rules. Phys. Rev. Lett., vol. 58, no. 9, pp. 949–952, 1987
Personnaz, L., Guyon, I. and Dreyfus, G.: Collective computational properties of neural networks: new learning mechanisms. Phys. Rev. A, vol. 34, pp. 4217–4228, 1986
Ouali, J., Saucier, G. and Trilhe, J.: A flexible wafer scale network. ICCD Conference, Rye Brook, (USA), September 1989
Personnaz, L., Guyon, I. and Dreyfus, G.: Designing a neural network satisfying a given set of constraints. In: Neural networks for computing, J.S. Denker ed., American Institute of Physics, 1986
Peterson, W.W. and Weldon, E.J.: Error correcting codes, MIT Press, 1972
Nature’s 11th international conference “How the brain works”, Cambridge (USA), September 1988. Nature vol.335, pp.489–491, October 1988
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Weinfeld, M. (1990). Integrated artificial neural networks: components for higher level architectures with new properties. In: Soulié, F.F., Hérault, J. (eds) Neurocomputing. NATO ASI Series, vol 68. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76153-9_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-76153-9_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76155-3
Online ISBN: 978-3-642-76153-9
eBook Packages: Springer Book Archive