Abstract
In [13] a freely expandable digital architecture for feedforward neural networks was described. This architecture exploits the use of stochastic bitstreams representing real valued signals. This paper proposes a hardware implementation of a recurrent neural network to form part of a novel system for solving the graph colouring problem [5], particulary relevant to frequency assignment in mobile telecommunications systems [7].
The core elements of the design are multi-state bitstream neurons, arranged in a pipelined architecture that allow for probabilistic connections between nodes, a fixed temperature cooling schedule, and control over the degree of parallelism used in the network update rule.
We also introduce the concept of hardware paging permitting the size of graph to be unconstrained and reducing the hardware overhead.
The highly regular and compact nature of the proposed circuitry, makes it an ideal candidate for utilizing the flexibility provided by FPGA's. In such a reconfigurable system, efficient problem specific hardware is easily generated.
Preview
Unable to display preview. Download preview PDF.
References
E. Aarts and J. Korst. Simulated Annealing and Boltzmann Machines. John Wiley & Sons, 1989.
Altera Corp. FLEX8000 programmable logic device family, 1993.
Altera Corp. FLEX10000 embedded programmable logic device family, 1995.
P. Burge. Parallel pruning. in private conversation, 1996.
P. Burge and J Shawe-Talyor. Bitstream neurons for graph colouring. Journal of Artificial Neural Networks, pages 443–448, 1995.
P. Burge, J. Shawe-Talyor, and J. Zerovnik. Graph colouring by maximal evidence edge adding. presented at the Udine Workshop on Approximate Solution Of Hard Combinatorial Problems.
B. Chamaret, S. Ubeda, and J. Zerovnik.A randomized algorithm for graph colouring applied to channel allocation in mobile telphone networks. In Operational Research Proceedings KOI'96, pages 25–30, 1996.
Dimacs colouring benchmarks. available via ftp at rutgers. dimacs. edu.
DIMACS Research Group. Clique and Colouring Problems, A Brief Introduction. Rutgers University, December 1992.
A. Petford and D. Welsh. A randomised 3-colouring algorithm. In Discrete Mathematics, volume 74, pages 253–261, 1989.
Barry Rising. Hardware design of multi-state bit stream neurons for graph colouring. Technical Report CSD-TR-96-12, Royal Holloway, June 1996.
J. Shawe-Taylor and J. Zerovnik. Generalised boltzmann machines. Technical Report CSD-TR-92-29, Royal Holloway, University of London, 1992.
M. van Daalen, P. Jeavons, and J. Shawe-Taylor. A stochastic neural architecture that exploits dynamically reconfigurable FPGAs. IEEE Workshop on FPGAS for custom computing machines, pages 202–211, 1993.
D. van den Bout. RIPP10 user manual, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rising, B., van Daalen, M., Burge, P., Shawe-Taylor, J. (1997). Parallel graph colouring using FPGAs. In: Luk, W., Cheung, P.Y.K., Glesner, M. (eds) Field-Programmable Logic and Applications. FPL 1997. Lecture Notes in Computer Science, vol 1304. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63465-7_217
Download citation
DOI: https://doi.org/10.1007/3-540-63465-7_217
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63465-2
Online ISBN: 978-3-540-69557-8
eBook Packages: Springer Book Archive