Abstract

An experiment using the phenomenon of percolation has been conducted to demonstrate the implementation of neural functionality (summing and sigmoid transfer). A simple analog approximation to digital percolation is implemented. The device consists of a piece of amorphous silicon with stochastic bit-stream optical inputs, in which a current percolating from one end to the other defines the neuron output, also in the form of a stochastic bit stream. Preliminary experimental results are presented.

© 1996 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. J. Shawe-Taylor, P. Jeavons, M. van Daalen, Connect. Sci. 3, 317 (1991).
    [CrossRef]
  2. T. J. Hall, M. van Daalen, UK patent application9420449.2 (October11, 1994).
  3. D. Pignon, T. J. Hall, “A quantised optical neural network with on-line learning,” submitted toInt. J. Optoelectron.
  4. A. G. Kirk, S. Jamieson, H. Imam, T. J. Hall, Opt. Comput. Process. 2, 293 (1992).
  5. P. K. Simpson, Artificial Neural Systems (Pergamon, Oxford, 1990).
  6. T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.
  7. D. Stauffer, A. Aharony, Introduction to Percolation Theory (Taylor & Francis, London, 1992).

1992 (1)

A. G. Kirk, S. Jamieson, H. Imam, T. J. Hall, Opt. Comput. Process. 2, 293 (1992).

1991 (1)

J. Shawe-Taylor, P. Jeavons, M. van Daalen, Connect. Sci. 3, 317 (1991).
[CrossRef]

Aharony, A.

D. Stauffer, A. Aharony, Introduction to Percolation Theory (Taylor & Francis, London, 1992).

Crossland, W. A.

T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.

Hall, T. J.

A. G. Kirk, S. Jamieson, H. Imam, T. J. Hall, Opt. Comput. Process. 2, 293 (1992).

T. J. Hall, M. van Daalen, UK patent application9420449.2 (October11, 1994).

T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.

D. Pignon, T. J. Hall, “A quantised optical neural network with on-line learning,” submitted toInt. J. Optoelectron.

Hands, M.

T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.

Imam, H.

A. G. Kirk, S. Jamieson, H. Imam, T. J. Hall, Opt. Comput. Process. 2, 293 (1992).

Jamieson, S.

A. G. Kirk, S. Jamieson, H. Imam, T. J. Hall, Opt. Comput. Process. 2, 293 (1992).

Jeavons, P.

J. Shawe-Taylor, P. Jeavons, M. van Daalen, Connect. Sci. 3, 317 (1991).
[CrossRef]

Kirk, A. G.

A. G. Kirk, S. Jamieson, H. Imam, T. J. Hall, Opt. Comput. Process. 2, 293 (1992).

Peiffer, W.

T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.

Pignon, D.

D. Pignon, T. J. Hall, “A quantised optical neural network with on-line learning,” submitted toInt. J. Optoelectron.

Shawe-Taylor, J.

J. Shawe-Taylor, P. Jeavons, M. van Daalen, Connect. Sci. 3, 317 (1991).
[CrossRef]

Shawe-Taylor, J. S.

T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.

Simpson, P. K.

P. K. Simpson, Artificial Neural Systems (Pergamon, Oxford, 1990).

Stauffer, D.

D. Stauffer, A. Aharony, Introduction to Percolation Theory (Taylor & Francis, London, 1992).

Thienpont, H.

T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.

van Daalen, M.

J. Shawe-Taylor, P. Jeavons, M. van Daalen, Connect. Sci. 3, 317 (1991).
[CrossRef]

T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.

T. J. Hall, M. van Daalen, UK patent application9420449.2 (October11, 1994).

Connect. Sci. (1)

J. Shawe-Taylor, P. Jeavons, M. van Daalen, Connect. Sci. 3, 317 (1991).
[CrossRef]

Opt. Comput. Process. (1)

A. G. Kirk, S. Jamieson, H. Imam, T. J. Hall, Opt. Comput. Process. 2, 293 (1992).

Other (5)

P. K. Simpson, Artificial Neural Systems (Pergamon, Oxford, 1990).

T. J. Hall, W. Peiffer, M. Hands, H. Thienpont, W. A. Crossland, J. S. Shawe-Taylor, M. van Daalen, in Optical Computing, Vol. 10 of 1995 OSA Technical Digest Series (Optical Society of America, Washington D.C., 1995), p. 210.

D. Stauffer, A. Aharony, Introduction to Percolation Theory (Taylor & Francis, London, 1992).

T. J. Hall, M. van Daalen, UK patent application9420449.2 (October11, 1994).

D. Pignon, T. J. Hall, “A quantised optical neural network with on-line learning,” submitted toInt. J. Optoelectron.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (5)

Fig. 1
Fig. 1

Digital percolation grid with bit-stream inputs and outputs.

Fig. 2
Fig. 2

Example of an eight-connected cell.

Fig. 3
Fig. 3

Computer simulation of a digital percolation grid. 16 × 16, 8 connected, 100 kbits per input.

Fig. 4
Fig. 4

Schematic of the analog percolation experiment. For clarity, the imaging optics are not shown.

Fig. 5
Fig. 5

Experimental result. 5 × 5 grid, 1500 bits, 60 steps.

Equations (2)

Equations on this page are rendered with MathJax. Learn more.

R off / R on N ( N 2 ) + 1 ,
y = 1 / [ 1 + exp ( a x + b ) ] ,

Metrics