Advertisement

FPGA implementation of an adaptable-size neural network

  • Andrés Pérez-Uribe
  • Eduardo Sanchez
Oral Presentations: Implementations Implementations: Dynamic and Massively Parallel Networks
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1112)

Abstract

Artificial neural networks achieve fast parallel processing via massively parallel non-linear computational elements. Most neural network models base their ability to adapt to problems on changing the strength of the interconnections between computational elements according to a given learning algorithm. However, constrained interconnection structures may limit such ability. Field programmable hardware devices allow the implementation of neural networks with in-circuit structure adaptation. This paper describes an FPGA implementation of the FAST (Flexible Adaptable-Size Topology) architecture, a neural network that dynamically changes its size. Since initial experiments indicated a good performance on pattern clustering tasks, we have applied our dynamic-structure FAST neural network to an image segmentation and recognition problem.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    A. Alpaydin: Neural Models of Incremental Supervised and Unsupervised Learning Thesis 863, Swiss Federal Institute of Technology, Lausanne, 1990.Google Scholar
  2. 2.
    G. Carpenter and S. Grossberg: ”Self-Organization of stable category recognition codes for analog pattern” Applied Optics Vol 26, 1987Google Scholar
  3. 3.
    D. Benitez Diaz and J. Garcma Quesada: “Learning Algorithm with Gaussian Membership Function for Fuzzy RBF Neural Networks” From Natural to Artificial Neural Computation Springer Verlag 1995.Google Scholar
  4. 4.
    E. Fiesler: ”Comparative Bibliography of Ontogenic Neural Networks” Proceedings of the International Conference on Artificial Neural Networks (ICANN'94) Google Scholar
  5. 5.
    B.Fritzke: ”Growing Cell Structures — a self-organizing network in k dimensions” Artificial Neural Networks 2 1992Google Scholar
  6. 6.
    “I-CUBE. The FPID Family Data Sheet” I-CUBE,Inc May, 1994Google Scholar
  7. 7.
    Y. Ohta: “Knowledge-Based Interpretation of Outdoor Natural Color Scenes” Pitman Advanced Publishing Program 1995Google Scholar
  8. 8.
    W. Pries and A. Thanailakis and H. C. Card: “Group Properties of Cellular Automata and VLSI Applications” IEEE Transactions on Computers December, 1986Google Scholar
  9. 9.
    S.M. Trimberger: Field-Programmable Gate Array Technology Kluwer Academic Publishers, Boston, 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Andrés Pérez-Uribe
    • 1
  • Eduardo Sanchez
    • 1
  1. 1.Logic Systems LaboratorySwiss Federal Institute of TechnologyLausanneSwitzerland

Personalised recommendations