Abstract

An optoelectronic neural network is presented that is designed to solve the assignment problem—or any similar optimization task given minimal adjustment—in both crossbar and banyan packet switches. We examine the design decisions made at the hardware, software, and algorithmic levels and indicate the associated effect on the system as a whole. Clearly detailed experimental results show the system’s robustness and performance due to the particular optoelectronic-algorithm combination used. The integration and packaging of such a system are also briefly discussed.

© 2004 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. K. J. Symington, A. J. Waddie, M. R. Taghizadeh, J. F. Snowdon, “A neural-network packet switch controller: scalability, performance, and network optimization,” IEEE Trans. Neural Net. 14, 28–34 (2003).
    [CrossRef]
  2. R. P. Webb, A. W. O’Neill, “Optoelectronic neural networks,” Br. Telecom. Technol. J. 10, 144–154 (1992).
  3. R. P. Webb, “Optoelectronic implementation of neural networks,” Int. J. Neural Syst. 4, 435–444 (1993).
    [CrossRef] [PubMed]
  4. A. Marrakchi, T. Troudet, “A neural net arbitrator for large crossbar packet switches,” IEEE Trans. Circuits Syst. 36, 1039–1041 (1989).
    [CrossRef]
  5. P. S. Rodríguez-Hernández, F. J. González-Castaño, J. M. Pousada-Carballo, U. M. García-Palomares, “Stochastic neural scheduler for real-time input-buffered packet switching,” Electron. Lett. 35, 1313–1314 (1999).
    [CrossRef]
  6. J. M. Pousada-Carballo, F. J. González-Castaño, P. S. Rodríguez-Hernández, U. M. García-Palomares, “High performance real-time neural scheduler for ATM switches,” IEEE Commun. Lett. 4, 372–374 (2000).
    [CrossRef]
  7. R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “An optoelectronic neural network scheduler for packet switches,” Appl. Opt. 39, 788–795 (2000).
    [CrossRef]
  8. P. Gupta, N. McKeown, “Designing and implementing a fast crossbar scheduler,” IEEE Micro. 19, 20–28 (1999).
    [CrossRef]
  9. K. J. Symington, J. F. Snowdon, A. J. Waddie, T. Yasue, M. R. Taghizadeh, “Optoelectronic neural networks,” Proceedings of the Second Conference on Postgraduate Research in Electronics, Photonics and Related Fields (Institution of Electrical Engineers, London, UK, 2000), pp. 182–187.
  10. K. J. Symington, A. J. Waddie, T. Yasue, M. R. Taghizadeh, J. F. Snowdon, “High performance optoelectronic neural network scheduler,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 12–14.
  11. P. W. Protzel, D. L. Palumbo, M. K. Arras, “Performance and fault-tolerance of neural networks for optimization,” IEEE Trans. Neural Net. 4, 600–614 (1993).
    [CrossRef]
  12. J. Ghosh, A. Hukkoo, A. Varma, “Neural networks for fast arbitration and switching noise reduction in large crossbars,” IEEE Trans. Circuits Syst. 38, 895–904 (1991).
    [CrossRef]
  13. R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “A Neural Network Scheduler for Packet Switches,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 1999), pp. 193–195.
  14. J. J. Hopfield, D. W. Tank, “Neural computation of decisions in optimisation problems,” Biol. Cybern. 52, 141–152 (1985).
  15. P. Blair, “Diffractive optical elements, design and fabrication issues,” Ph.D. dissertation (Heriot-Watt University, Edinburgh, UK, 1995).
  16. A. Vasara, M. R. Taghizadeh, J. Turunen, J. Westerholm, E. Noponen, H. Ichikawa, J. M. Miller, T. Jaakkola, S. Kuisma, “Binary surface-relief gratings for array illumination in digital optics,” Appl. Opt. 31, 3320–3336 (1992).
    [CrossRef] [PubMed]
  17. K. Ballüder, M. R. Taghizadeh, “Optimised phase quantisation for diffractive elements using a bias phase,” Opt. Lett. 24, 1756–1758 (1999).
    [CrossRef]
  18. J. W. Goodman, Introduction to Fourier Optics, 2nd. Ed. (McGraw-Hill, New York, 1996).
  19. M. A. Holler, “VLSI implementations of learning and memory systems: a review,” in Advances in Neural Information Processing Systems 3 (Morgan Kaufmann, San Mateo, Calif., 1991), pp. 993–1000.
  20. R. Stone, J. Kim, P. Guilfoyle, “High performance shock hardened optoelectronic communications module,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 105–107.
  21. P. Ferguson, G. Huston, Quality of Service: Delivering QoS on the Internet and in Corporate Networks (Wiley, New York, 1998).

2003 (1)

K. J. Symington, A. J. Waddie, M. R. Taghizadeh, J. F. Snowdon, “A neural-network packet switch controller: scalability, performance, and network optimization,” IEEE Trans. Neural Net. 14, 28–34 (2003).
[CrossRef]

2000 (2)

J. M. Pousada-Carballo, F. J. González-Castaño, P. S. Rodríguez-Hernández, U. M. García-Palomares, “High performance real-time neural scheduler for ATM switches,” IEEE Commun. Lett. 4, 372–374 (2000).
[CrossRef]

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “An optoelectronic neural network scheduler for packet switches,” Appl. Opt. 39, 788–795 (2000).
[CrossRef]

1999 (3)

P. S. Rodríguez-Hernández, F. J. González-Castaño, J. M. Pousada-Carballo, U. M. García-Palomares, “Stochastic neural scheduler for real-time input-buffered packet switching,” Electron. Lett. 35, 1313–1314 (1999).
[CrossRef]

K. Ballüder, M. R. Taghizadeh, “Optimised phase quantisation for diffractive elements using a bias phase,” Opt. Lett. 24, 1756–1758 (1999).
[CrossRef]

P. Gupta, N. McKeown, “Designing and implementing a fast crossbar scheduler,” IEEE Micro. 19, 20–28 (1999).
[CrossRef]

1993 (2)

P. W. Protzel, D. L. Palumbo, M. K. Arras, “Performance and fault-tolerance of neural networks for optimization,” IEEE Trans. Neural Net. 4, 600–614 (1993).
[CrossRef]

R. P. Webb, “Optoelectronic implementation of neural networks,” Int. J. Neural Syst. 4, 435–444 (1993).
[CrossRef] [PubMed]

1992 (2)

1991 (1)

J. Ghosh, A. Hukkoo, A. Varma, “Neural networks for fast arbitration and switching noise reduction in large crossbars,” IEEE Trans. Circuits Syst. 38, 895–904 (1991).
[CrossRef]

1989 (1)

A. Marrakchi, T. Troudet, “A neural net arbitrator for large crossbar packet switches,” IEEE Trans. Circuits Syst. 36, 1039–1041 (1989).
[CrossRef]

1985 (1)

J. J. Hopfield, D. W. Tank, “Neural computation of decisions in optimisation problems,” Biol. Cybern. 52, 141–152 (1985).

Arras, M. K.

P. W. Protzel, D. L. Palumbo, M. K. Arras, “Performance and fault-tolerance of neural networks for optimization,” IEEE Trans. Neural Net. 4, 600–614 (1993).
[CrossRef]

Ballüder, K.

Blair, P.

P. Blair, “Diffractive optical elements, design and fabrication issues,” Ph.D. dissertation (Heriot-Watt University, Edinburgh, UK, 1995).

Ferguson, P.

P. Ferguson, G. Huston, Quality of Service: Delivering QoS on the Internet and in Corporate Networks (Wiley, New York, 1998).

García-Palomares, U. M.

J. M. Pousada-Carballo, F. J. González-Castaño, P. S. Rodríguez-Hernández, U. M. García-Palomares, “High performance real-time neural scheduler for ATM switches,” IEEE Commun. Lett. 4, 372–374 (2000).
[CrossRef]

P. S. Rodríguez-Hernández, F. J. González-Castaño, J. M. Pousada-Carballo, U. M. García-Palomares, “Stochastic neural scheduler for real-time input-buffered packet switching,” Electron. Lett. 35, 1313–1314 (1999).
[CrossRef]

Ghosh, J.

J. Ghosh, A. Hukkoo, A. Varma, “Neural networks for fast arbitration and switching noise reduction in large crossbars,” IEEE Trans. Circuits Syst. 38, 895–904 (1991).
[CrossRef]

González-Castaño, F. J.

J. M. Pousada-Carballo, F. J. González-Castaño, P. S. Rodríguez-Hernández, U. M. García-Palomares, “High performance real-time neural scheduler for ATM switches,” IEEE Commun. Lett. 4, 372–374 (2000).
[CrossRef]

P. S. Rodríguez-Hernández, F. J. González-Castaño, J. M. Pousada-Carballo, U. M. García-Palomares, “Stochastic neural scheduler for real-time input-buffered packet switching,” Electron. Lett. 35, 1313–1314 (1999).
[CrossRef]

Goodman, J. W.

J. W. Goodman, Introduction to Fourier Optics, 2nd. Ed. (McGraw-Hill, New York, 1996).

Guilfoyle, P.

R. Stone, J. Kim, P. Guilfoyle, “High performance shock hardened optoelectronic communications module,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 105–107.

Gupta, P.

P. Gupta, N. McKeown, “Designing and implementing a fast crossbar scheduler,” IEEE Micro. 19, 20–28 (1999).
[CrossRef]

Holler, M. A.

M. A. Holler, “VLSI implementations of learning and memory systems: a review,” in Advances in Neural Information Processing Systems 3 (Morgan Kaufmann, San Mateo, Calif., 1991), pp. 993–1000.

Hopfield, J. J.

J. J. Hopfield, D. W. Tank, “Neural computation of decisions in optimisation problems,” Biol. Cybern. 52, 141–152 (1985).

Hukkoo, A.

J. Ghosh, A. Hukkoo, A. Varma, “Neural networks for fast arbitration and switching noise reduction in large crossbars,” IEEE Trans. Circuits Syst. 38, 895–904 (1991).
[CrossRef]

Huston, G.

P. Ferguson, G. Huston, Quality of Service: Delivering QoS on the Internet and in Corporate Networks (Wiley, New York, 1998).

Ichikawa, H.

Jaakkola, T.

Kim, J.

R. Stone, J. Kim, P. Guilfoyle, “High performance shock hardened optoelectronic communications module,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 105–107.

Kuisma, S.

Marrakchi, A.

A. Marrakchi, T. Troudet, “A neural net arbitrator for large crossbar packet switches,” IEEE Trans. Circuits Syst. 36, 1039–1041 (1989).
[CrossRef]

McKeown, N.

P. Gupta, N. McKeown, “Designing and implementing a fast crossbar scheduler,” IEEE Micro. 19, 20–28 (1999).
[CrossRef]

Miller, J. M.

Noponen, E.

O’Neill, A. W.

R. P. Webb, A. W. O’Neill, “Optoelectronic neural networks,” Br. Telecom. Technol. J. 10, 144–154 (1992).

Palumbo, D. L.

P. W. Protzel, D. L. Palumbo, M. K. Arras, “Performance and fault-tolerance of neural networks for optimization,” IEEE Trans. Neural Net. 4, 600–614 (1993).
[CrossRef]

Pousada-Carballo, J. M.

J. M. Pousada-Carballo, F. J. González-Castaño, P. S. Rodríguez-Hernández, U. M. García-Palomares, “High performance real-time neural scheduler for ATM switches,” IEEE Commun. Lett. 4, 372–374 (2000).
[CrossRef]

P. S. Rodríguez-Hernández, F. J. González-Castaño, J. M. Pousada-Carballo, U. M. García-Palomares, “Stochastic neural scheduler for real-time input-buffered packet switching,” Electron. Lett. 35, 1313–1314 (1999).
[CrossRef]

Protzel, P. W.

P. W. Protzel, D. L. Palumbo, M. K. Arras, “Performance and fault-tolerance of neural networks for optimization,” IEEE Trans. Neural Net. 4, 600–614 (1993).
[CrossRef]

Rodríguez-Hernández, P. S.

J. M. Pousada-Carballo, F. J. González-Castaño, P. S. Rodríguez-Hernández, U. M. García-Palomares, “High performance real-time neural scheduler for ATM switches,” IEEE Commun. Lett. 4, 372–374 (2000).
[CrossRef]

P. S. Rodríguez-Hernández, F. J. González-Castaño, J. M. Pousada-Carballo, U. M. García-Palomares, “Stochastic neural scheduler for real-time input-buffered packet switching,” Electron. Lett. 35, 1313–1314 (1999).
[CrossRef]

Snowdon, J. F.

K. J. Symington, A. J. Waddie, M. R. Taghizadeh, J. F. Snowdon, “A neural-network packet switch controller: scalability, performance, and network optimization,” IEEE Trans. Neural Net. 14, 28–34 (2003).
[CrossRef]

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “An optoelectronic neural network scheduler for packet switches,” Appl. Opt. 39, 788–795 (2000).
[CrossRef]

K. J. Symington, J. F. Snowdon, A. J. Waddie, T. Yasue, M. R. Taghizadeh, “Optoelectronic neural networks,” Proceedings of the Second Conference on Postgraduate Research in Electronics, Photonics and Related Fields (Institution of Electrical Engineers, London, UK, 2000), pp. 182–187.

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “A Neural Network Scheduler for Packet Switches,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 1999), pp. 193–195.

K. J. Symington, A. J. Waddie, T. Yasue, M. R. Taghizadeh, J. F. Snowdon, “High performance optoelectronic neural network scheduler,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 12–14.

Stone, R.

R. Stone, J. Kim, P. Guilfoyle, “High performance shock hardened optoelectronic communications module,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 105–107.

Symington, K. J.

K. J. Symington, A. J. Waddie, M. R. Taghizadeh, J. F. Snowdon, “A neural-network packet switch controller: scalability, performance, and network optimization,” IEEE Trans. Neural Net. 14, 28–34 (2003).
[CrossRef]

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “An optoelectronic neural network scheduler for packet switches,” Appl. Opt. 39, 788–795 (2000).
[CrossRef]

K. J. Symington, J. F. Snowdon, A. J. Waddie, T. Yasue, M. R. Taghizadeh, “Optoelectronic neural networks,” Proceedings of the Second Conference on Postgraduate Research in Electronics, Photonics and Related Fields (Institution of Electrical Engineers, London, UK, 2000), pp. 182–187.

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “A Neural Network Scheduler for Packet Switches,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 1999), pp. 193–195.

K. J. Symington, A. J. Waddie, T. Yasue, M. R. Taghizadeh, J. F. Snowdon, “High performance optoelectronic neural network scheduler,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 12–14.

Taghizadeh, M. R.

K. J. Symington, A. J. Waddie, M. R. Taghizadeh, J. F. Snowdon, “A neural-network packet switch controller: scalability, performance, and network optimization,” IEEE Trans. Neural Net. 14, 28–34 (2003).
[CrossRef]

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “An optoelectronic neural network scheduler for packet switches,” Appl. Opt. 39, 788–795 (2000).
[CrossRef]

K. Ballüder, M. R. Taghizadeh, “Optimised phase quantisation for diffractive elements using a bias phase,” Opt. Lett. 24, 1756–1758 (1999).
[CrossRef]

A. Vasara, M. R. Taghizadeh, J. Turunen, J. Westerholm, E. Noponen, H. Ichikawa, J. M. Miller, T. Jaakkola, S. Kuisma, “Binary surface-relief gratings for array illumination in digital optics,” Appl. Opt. 31, 3320–3336 (1992).
[CrossRef] [PubMed]

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “A Neural Network Scheduler for Packet Switches,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 1999), pp. 193–195.

K. J. Symington, J. F. Snowdon, A. J. Waddie, T. Yasue, M. R. Taghizadeh, “Optoelectronic neural networks,” Proceedings of the Second Conference on Postgraduate Research in Electronics, Photonics and Related Fields (Institution of Electrical Engineers, London, UK, 2000), pp. 182–187.

K. J. Symington, A. J. Waddie, T. Yasue, M. R. Taghizadeh, J. F. Snowdon, “High performance optoelectronic neural network scheduler,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 12–14.

Tank, D. W.

J. J. Hopfield, D. W. Tank, “Neural computation of decisions in optimisation problems,” Biol. Cybern. 52, 141–152 (1985).

Troudet, T.

A. Marrakchi, T. Troudet, “A neural net arbitrator for large crossbar packet switches,” IEEE Trans. Circuits Syst. 36, 1039–1041 (1989).
[CrossRef]

Turunen, J.

Varma, A.

J. Ghosh, A. Hukkoo, A. Varma, “Neural networks for fast arbitration and switching noise reduction in large crossbars,” IEEE Trans. Circuits Syst. 38, 895–904 (1991).
[CrossRef]

Vasara, A.

Waddie, A. J.

K. J. Symington, A. J. Waddie, M. R. Taghizadeh, J. F. Snowdon, “A neural-network packet switch controller: scalability, performance, and network optimization,” IEEE Trans. Neural Net. 14, 28–34 (2003).
[CrossRef]

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “An optoelectronic neural network scheduler for packet switches,” Appl. Opt. 39, 788–795 (2000).
[CrossRef]

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “A Neural Network Scheduler for Packet Switches,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 1999), pp. 193–195.

K. J. Symington, J. F. Snowdon, A. J. Waddie, T. Yasue, M. R. Taghizadeh, “Optoelectronic neural networks,” Proceedings of the Second Conference on Postgraduate Research in Electronics, Photonics and Related Fields (Institution of Electrical Engineers, London, UK, 2000), pp. 182–187.

K. J. Symington, A. J. Waddie, T. Yasue, M. R. Taghizadeh, J. F. Snowdon, “High performance optoelectronic neural network scheduler,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 12–14.

Webb, R. P.

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “An optoelectronic neural network scheduler for packet switches,” Appl. Opt. 39, 788–795 (2000).
[CrossRef]

R. P. Webb, “Optoelectronic implementation of neural networks,” Int. J. Neural Syst. 4, 435–444 (1993).
[CrossRef] [PubMed]

R. P. Webb, A. W. O’Neill, “Optoelectronic neural networks,” Br. Telecom. Technol. J. 10, 144–154 (1992).

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “A Neural Network Scheduler for Packet Switches,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 1999), pp. 193–195.

Westerholm, J.

Yasue, T.

K. J. Symington, J. F. Snowdon, A. J. Waddie, T. Yasue, M. R. Taghizadeh, “Optoelectronic neural networks,” Proceedings of the Second Conference on Postgraduate Research in Electronics, Photonics and Related Fields (Institution of Electrical Engineers, London, UK, 2000), pp. 182–187.

K. J. Symington, A. J. Waddie, T. Yasue, M. R. Taghizadeh, J. F. Snowdon, “High performance optoelectronic neural network scheduler,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 12–14.

Appl. Opt. (2)

Biol. Cybern. (1)

J. J. Hopfield, D. W. Tank, “Neural computation of decisions in optimisation problems,” Biol. Cybern. 52, 141–152 (1985).

Br. Telecom. Technol. J. (1)

R. P. Webb, A. W. O’Neill, “Optoelectronic neural networks,” Br. Telecom. Technol. J. 10, 144–154 (1992).

Electron. Lett. (1)

P. S. Rodríguez-Hernández, F. J. González-Castaño, J. M. Pousada-Carballo, U. M. García-Palomares, “Stochastic neural scheduler for real-time input-buffered packet switching,” Electron. Lett. 35, 1313–1314 (1999).
[CrossRef]

IEEE Commun. Lett. (1)

J. M. Pousada-Carballo, F. J. González-Castaño, P. S. Rodríguez-Hernández, U. M. García-Palomares, “High performance real-time neural scheduler for ATM switches,” IEEE Commun. Lett. 4, 372–374 (2000).
[CrossRef]

IEEE Micro. (1)

P. Gupta, N. McKeown, “Designing and implementing a fast crossbar scheduler,” IEEE Micro. 19, 20–28 (1999).
[CrossRef]

IEEE Trans. Circuits Syst. (2)

J. Ghosh, A. Hukkoo, A. Varma, “Neural networks for fast arbitration and switching noise reduction in large crossbars,” IEEE Trans. Circuits Syst. 38, 895–904 (1991).
[CrossRef]

A. Marrakchi, T. Troudet, “A neural net arbitrator for large crossbar packet switches,” IEEE Trans. Circuits Syst. 36, 1039–1041 (1989).
[CrossRef]

IEEE Trans. Neural Net. (2)

P. W. Protzel, D. L. Palumbo, M. K. Arras, “Performance and fault-tolerance of neural networks for optimization,” IEEE Trans. Neural Net. 4, 600–614 (1993).
[CrossRef]

K. J. Symington, A. J. Waddie, M. R. Taghizadeh, J. F. Snowdon, “A neural-network packet switch controller: scalability, performance, and network optimization,” IEEE Trans. Neural Net. 14, 28–34 (2003).
[CrossRef]

Int. J. Neural Syst. (1)

R. P. Webb, “Optoelectronic implementation of neural networks,” Int. J. Neural Syst. 4, 435–444 (1993).
[CrossRef] [PubMed]

Opt. Lett. (1)

Other (8)

J. W. Goodman, Introduction to Fourier Optics, 2nd. Ed. (McGraw-Hill, New York, 1996).

M. A. Holler, “VLSI implementations of learning and memory systems: a review,” in Advances in Neural Information Processing Systems 3 (Morgan Kaufmann, San Mateo, Calif., 1991), pp. 993–1000.

R. Stone, J. Kim, P. Guilfoyle, “High performance shock hardened optoelectronic communications module,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 105–107.

P. Ferguson, G. Huston, Quality of Service: Delivering QoS on the Internet and in Corporate Networks (Wiley, New York, 1998).

P. Blair, “Diffractive optical elements, design and fabrication issues,” Ph.D. dissertation (Heriot-Watt University, Edinburgh, UK, 1995).

R. P. Webb, A. J. Waddie, K. J. Symington, M. R. Taghizadeh, J. F. Snowdon, “A Neural Network Scheduler for Packet Switches,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 1999), pp. 193–195.

K. J. Symington, J. F. Snowdon, A. J. Waddie, T. Yasue, M. R. Taghizadeh, “Optoelectronic neural networks,” Proceedings of the Second Conference on Postgraduate Research in Electronics, Photonics and Related Fields (Institution of Electrical Engineers, London, UK, 2000), pp. 182–187.

K. J. Symington, A. J. Waddie, T. Yasue, M. R. Taghizadeh, J. F. Snowdon, “High performance optoelectronic neural network scheduler,” Digest of the Topical Meeting on Optics in Computing (Optical Society of America, Washington, D.C., 2001), pp. 12–14.

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 (15)

Fig. 1
Fig. 1

Neural-network crossbar switch controller. Based on the connections requested by incoming packets, the neural network chooses an optimal solution, sets the appropriate crossbar switches, and then selects the chosen packets.

Fig. 2
Fig. 2

Neural-network controller for a self-routing multistage banyan switch. Here the neural network selects an optimal packet solution and notifies the input buffers. It does not directly control the switching network.

Fig. 3
Fig. 3

Neural-network interconnect pattern mapped to an N = 5 element crossbar switch. Neuron y 22 receives inhibitory input from all the other neurons in the same row and column. Note that m = n = N and b is the bias.

Fig. 4
Fig. 4

Simulated rates of convergence against network size N for varying switch sizes in both digital and analog versions. The digital system exhibits superior scalability.

Fig. 5
Fig. 5

Second-generation system overview. This is an N = 8 neural network in which the ferrite cores suppress the noise. DOE, diffractive optic element.

Fig. 6
Fig. 6

Logical overview of the second-generation system. The lines through the optical system indicate which VCSELs are associated with which detectors.

Fig. 7
Fig. 7

DOE interconnect patterns for (a) a crossbar switch and (b) a banyan switch produced when a single beam is incident to the element. Each spot represents a diffracted order. Since this is a two dimensional pattern, each order must be classified in both x and y directions with the center of the pattern representing the origin. Both patterns shown here are specifically designed for an N = 8 system.

Fig. 8
Fig. 8

Diffracted pattern produced when four VCSEL channels are diffracted onto the detector array. Part (a) illustrates the result theoretically and part (b) shows a photograph of the same pattern in the aligned system.

Fig. 9
Fig. 9

Validity as a function of A and b (N = 8) for the crossbar interconnect.

Fig. 10
Fig. 10

Average number of neurons on as a function of A and b (N = 8) for the crossbar interconnect.

Fig. 11
Fig. 11

Crossbar results as functions of the load (N = 6, b = 12).

Fig. 12
Fig. 12

Validity as a function of A and b (N = 8) for the banyan interconnect.

Fig. 13
Fig. 13

Average number of neurons on as a function of A and b (N = 8) for the banyan interconnect.

Fig. 14
Fig. 14

Banyan results as functions of the load (N = 6, b = 12).

Fig. 15
Fig. 15

Evolution of the neurons during a single optimization. Winning neurons switch on, the rest switch off.

Equations (4)

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

xijt=iijxijt-1-A kim wkjykj-A kjn wikyik+b,
yij=11+exp-βxijt,
Ay1b.
Ay1b,

Metrics