Advertisement

pRAM: The Probabilistic RAM Neural Processor

  • Trevor G. Clarkson
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 74)

Abstract

The pRAM has been implemented as a VLSI processor incorporating 256 neurons with on-chip learning. Several such processors may be connected to form larger networks. The pRAM was originally conceived to model the noisy release of neurotransmitter vesicles in synaptic connections. In a network, it forms n-tuples and may operate as a noisy lookup table with generalization. The reinforcement training used is also biologically realistic and has a scope ranging from a single neuron to the whole network, the architecture being user-defined.

Keywords

Spike Train Connection Admission Control Automatic Target Recognition Penalty Signal Global Reward 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Aleksander I., Microcircuit learning computers, Mills and Boon, London, 1971.MATHGoogle Scholar
  2. [2]
    Clarkson T. G., Gorse D., Taylor J. G., Hardware-realizable models of neural processing, Proc. of IEE International Conference on Artificial Neural Networks, London, 242–246, 1989Google Scholar
  3. [3]
    Clarkson T. G., Gorse D., Taylor J. G., Ng C. K., Learning Probabilistic RAM Nets Using VLSI Structures, IEEE Transactions on Computers, 41 (12), 1552–1561, 1992CrossRefGoogle Scholar
  4. [4]
    Clarkson T. G., Ng C. K., Christodoulou C., Guan Y., The pRAM: An Adaptive VLSI Chip, IEEE Transactions on Neural Networks, Special Issue on Neural Network Hardware, 4 (3), 408–412, 1993CrossRefGoogle Scholar
  5. [5]
    Clarkson T. G., Gorse D., Taylor J. G., Biologically plausible learning in hardware realizable nets, Proc. ICANN91 Conf, Helsinki, 195–199, 1991Google Scholar
  6. [6]
    Ramanan S., Petersen R., Clarkson T. G., Taylor J. G., pRAM nets for detection of small targets in sequences of infra-red images, Neural Networks, 8 (7/8), 1227–1237, 1995CrossRefGoogle Scholar
  7. [7]
    Clarkson T. G., Automatic Target Recognition using Neural Networks, Neural Network World, 6 /95, 861–871, 1995Google Scholar
  8. [8]
    Ramanan S., Petersen R. S., Clarkson T. G., Taylor J. G., Adaptive learning rate for training pyramidal pRAM nets, Proc. ICANN’94, 1360–13631, 1994Google Scholar
  9. [9]
    Ramanan S., Clarkson T. G., Taylor J. G., An adaptive algorithm for training pRAM neural networks on unbalanced data sets, Electronics Letters, 34 (13), 1335–1336, 1998CrossRefGoogle Scholar
  10. [10]
    Clarkson T. G., Automatic Target Recognition using Neural Networks, Neural Network World, 6 /95, 861–871, 1995Google Scholar
  11. [11]
    Guan Y., Clarkson T. G., Taylor J. G., A noisy training method for digit recognition using pRAM neural networks, Proc. IJCNN’92 Conference, Beijing, I-673/678, 1992Google Scholar
  12. [12]
    Guan Y., Clarkson T. G., Aspects of pRAM training in noise, Proc. WNNW’93 Workshop, York, 111–116, 1993Google Scholar
  13. [13]
    El-Mousa A., Clarkson T. G., Output Coding in Noisy-Trained pRAM Neural Networks, Proc. ICANN’94, 1356–1359, 1994Google Scholar
  14. [14]
    Guan Y., Clarkson T. G., Taylor J. G., Learning transformed prototypes (LTP) - a statistical pattern classification technique of neural networks, From Natural to Artificial Neural Computation, Eds. Mira and Sandoval, Springer-Verlag, 441–447, 1995Google Scholar
  15. [15]
    El Mousa A. H., Clarkson T. G., An improved hardware-realizable learning algorithm for pyramidal feed-forward pRAM-based ANNs, Proc. ANN’95, IEE 4th International Conference on Artificial Neural Networks, Cambridge, 495–498, 1995Google Scholar
  16. [16]
    Clarkson T. G., Guan Y., Gorse D., Taylor J. G., Generalization in Probabilistic RAM Nets, IEEE Transactions on Neural Networks, 4 (2), 360–364, 1993CrossRefGoogle Scholar
  17. [17]
    Guan Y., Clarkson T. G., Taylor J. G., Gorse D., Optimal attractor distributions and generalization in feed-forward pRAM nets, Proc. BNNS Meeting, Birmingham, 1993Google Scholar
  18. [18]
    Ding Y., Guan Y., Clarkson T. G., Clark R. P., The Back Thermal Symmetry Identification by pRAM Neural Networks, Proc. ANN’95, IEE 4th International Conference on Artificial Neural Networks, Cambridge, 437441, 1995Google Scholar
  19. [19]
    Ding Y., Clarkson T. G., Extracting the directional image of fingerprints by a neural algorithm, WNNW’95, Canterbury, 1995Google Scholar
  20. [20]
    Oldfield M., Underwood C. I., Clarkson T. G., Spacecraft Autonomy Via Probabilistic RAM (pRAM) Artificial Neural Networks, Proceedings of the 12th AMSAT-UK Colloquium 1997, University of Surrey, 102–110, 1997Google Scholar
  21. [21]
    Oldfield M. K., Underwood C. I., Clarkson T. G., Evaluation Of The pRAM Neural Network Processor For Use In Ionizing Radiation Environments, IEEE Radiation Effects In Electronics Components Conference, Oxford, September 14–15, 1998Google Scholar
  22. [22]
    Balaskas I., Jun I., Panteli P. L., Clarkson T. G., Adaptive ATM network traffic modeling using a combined source model, Proc. ICC’98, Atlanta, 238–242, 1998Google Scholar
  23. [23]
    Krasniqi X., Onyiagha G., Clarkson T. G., Performance evaluation of a distributed ATM switch architecture, International Network Conference (INC’98), Plymouth, 1998Google Scholar
  24. [24]
    Jun I., Panteli P. L., Clarkson T. G., Simulation Analysis with a Measurement based Connection Admission Control on a European ATM Network, 6th IFIP workshop on performance modeling and evaluation of ATM networks (ATM’98), Bradford, 1998Google Scholar
  25. [25]
    Onyiagha G., Krasniqi X., Clarkson T. G., OpLIAC - Open-loop intelligent access control for interworking LAN and ATM networks, 6th IFIP workshop on performance modeling and evaluation of ATM networks (ATM’98), Bradford, 1998Google Scholar
  26. [26]
    Balestrieri F., Panteli P. L. et. al., ATM connection admission control using pRAM-based artificial neural networks, 6th IFIP workshop on performance modeling and evaluation of ATM networks (ATM’98), Bradford, 1998Google Scholar
  27. [27]
    Onyiagha G., Balestrieri F. et. al., Optimal quality of service guarantees for noisy packet data networks, IEEE Globecom’98, Sydney, Australia, 13–18, 1998Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Trevor G. Clarkson
    • 1
  1. 1.Department of Electronic EngineeringKing’s College LondonLondonUK

Personalised recommendations