A Continuous Restricted Boltzmann Machine with a Hardware- Amenable Learning Algorithm (original) (raw)

Abstract

This paper proposes a continuous stochastic generative model that offers an improved ability to model analogue data, with a simple and reliable learning algorithm. The architecture forms a continuous restricted Boltzmann Machine, with a novel learning algorithm. The capabilities of the model are demonstrated with both artificial and real data.

Preview

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Hinton, G.E.: Training Products of Experts by minimising contrastive divergence. Technical Report: Gatsby Comp. Neuroscience Unit, no.TR2000-004. (2000)
    Google Scholar
  2. Smolensky, P.: Information processing in dynamical systems: Foundations of harmony theory. Parallel Distributed Processing. Vol. 1 (1986) 195–281
    Google Scholar
  3. Murray, A.F.: Novelty detection using products of simple experts-A potential architecture for embedded systems. Neural Networks 14(9) (2001) 1257–1264
    Article Google Scholar
  4. Teh, Y.W., Hinton, G.E.: Rate-coded Restricted Boltzmann Machine for face recognition. Advances in Neural Information Processing Systems, Vol. 13 (2001)
    Google Scholar
  5. Woodburn, R.J., Astaras, A.A., Dalzell, R.W., Murray, A.F., McNeill, D.K.: Computing with uncertainty in probabilistic neural networks on silicon. Proc. 2nd Int. ICSC Symp. on Neural Computation. (1999) 470–476
    Google Scholar
  6. Movellan, J.R.: A learning theorem for networks at detailed stochastic equilibrium. Neural Computation, Vol. 10(5) (1998) 1157–1178
    Article Google Scholar
  7. Movellan, J.R., Mineiro, P., William, R.J.: A Monte-Carlo EM approach for partially observable diffusion process: Theory and applications to neural network. Neural Computation (In Press)
    Google Scholar
  8. Marks, T.K., Movellan, J.R.: Diffusion networks, products of experts, and factor analysis. UCSD MPLab Technical Report, 2001.02. (2001)
    Google Scholar
  9. Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Nat. Academy of Science of the USA, Vol. 81(10). (1984) 3088–3092
    Article Google Scholar
  10. Tarassenko, L., Clifford G.: Detection of ectopic beats in the electrocardiogram using an Auto-associative neural network. Neural Processing Letters, Vol. 14(1) (2001) 15–25
    Article MATH Google Scholar
  11. Fleury, P., Woodburn, R.J., Murray, A.F.: Matching analogue hardware with applications using the Products of Experts algorithm. Proc. IEEE European Symp. on Artificial Neural Networks. (2001)63–67
    Google Scholar

Download references

Author information

Authors and Affiliations

  1. Dept. of Electronics and Electrical Engineering, University of Edinburgh, Mayfield Rd., Edinburgh, EH9 3JL, UK
    Hsin Chen & Alan Murray

Authors

  1. Hsin Chen
  2. Alan Murray

Editor information

Editors and Affiliations

  1. ETS Informática, Universidad Autónoma de Madrid, 28049, Madrid, Spain
    José R. Dorronsoro

Rights and permissions

© 2002 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Chen, H., Murray, A. (2002). A Continuous Restricted Boltzmann Machine with a Hardware- Amenable Learning Algorithm. In: Dorronsoro, J.R. (eds) Artificial Neural Networks — ICANN 2002. ICANN 2002. Lecture Notes in Computer Science, vol 2415. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46084-5\_58

Download citation

Keywords

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.

Publish with us