‘Quantum’ Parallel computation with neural networks

Doctoral thesis English OPEN
Burles, Nathan John (2010)

Correlation matrix memories have been successfully applied to many domains. This work implements a production system put forward in [Austin, 2003], to demonstrate its viability as an efficient rule-chaining process. Background information on rule-chaining and CMMs is given, followed by a review of the proposed production system. Throughout the iterative development process, experimentation is performed in order to investigate the effects of changing the properties of vectors used in this system. The results show that generating vectors using the algorithm proposed in [Baum, 1988] with a weight close to log2 of the vector length provides the highest storage capacity. The simple system implemented in this work performs rule-chaining effectively. This leads to the conclusion that the proposed production system is viable, and that this area warrants further work.
  • References (48)
    48 references, page 1 of 5

    [1] Jim Austin, "A production system architecture using a Neural Associative Memory," University of York, York, Unpublished 2003.

    [2] Jim Austin, "A Review of RAM based Neural Networks," in Fourth International Conference on Microelectronics, Turin, 1994, pp. 58-66.

    [3] Jim Austin, "Distributed Associative Memories for High Speed Symbolic Reasoning," Fuzzy Sets and Systems, vol. 82, no. 2, pp. 223-233, September 1996.

    [4] Jim Austin, "Parallel Distributed Computation," in International Conference on Artificial Neural Networks, Brighton, 1992.

    [5] Jim Austin, "Uncertain Reasoning with RAM based Neural Networks," Journal of Intelligent Systems, vol. 2, no. 4, pp. 121-154, November 1990.

    [6] Jim Austin and Richard Filer, "Using Neural Networks for Inferencing in Expert Systems," in Neural Networks and Their Applications, John G Taylor, Ed. New York, United States of America: John Wiley & Sons, 1996, ch. 16, pp. 243-.

    [7] Jim Austin and Thomas J Stonham, "The ADAM Associative Memory," University of York, York, Yellow Report YCS 94, 1986.

    [8] Eric B Baum, J Moody, and F Wilczek, "Internal representations for associative memory," Biological Cybernetics, vol. 59, no. 4-5, pp. 217-228, September 1988.

    [9] Rafal Bogacz and Christophe Giraud-Carrier, "A Novel Modular Neural Architecture for RuleBased and Similarity-Based Reasoning," in Hybrid Neural Systems, Stefan Wermter and Ron Sun, Eds. Heidelberg, Germany: Springer-Verlag, 2000, pp. 63-77.

    [10] Samuel Braunstein. (2009, October) Quantum Information Processing Course website. [Online]. http://www-course.cs.york.ac.uk/qip

  • Metrics
    views in OpenAIRE
    views in local repository
    downloads in local repository

    The information is available from the following content providers:

    From Number Of Views Number Of Downloads
    White Rose Research Online - IRUS-UK 0 1
Share - Bookmark