Skip to main content
SpringerLink
Log in
Book cover

Encyclopedia of Computational Neuroscience pp 1–6Cite as

Boltzmann Machine

  • 283 Accesses

Synonyms

Noisy neural network; Stochastic Hopfield network

Definition

Boltzmann machines are usually defined as neural networks in which the input–output relationship is stochastic instead of deterministic (as it is in the original Hopfield network). Then, Boltzmann machines are normally defined as stochastic versions of the Hopfield model or other attractor neural networks. A main difference between Hopfield networks and Boltzmann machines is that whereas in Hopfield networks, the deterministic dynamics brings the state of the system downhill, toward the stable minima of some energy function related with some information content, in a Boltzmann machine, such prescribedstates of the system cannot be reached due to stochastic fluctuations. For a Boltzmann machine, then, the steady state of the system is characterized by an equilibrium probability distribution to be in such states, which is given as a function of the energy of such states by the Boltzmann distribution. The inherent...

This is a preview of subscription content, log in via an institution.

References

  • Ackley DH, Hinton GE, Sejnowski TJ (1985) A learning algorithm for Boltzmann machines. Cogn Sci 9(1):147–169

    Article  Google Scholar 

  • Hinton GE, Sejnowski TJ (1983a) Analyzing cooperative computation. In: Proceedings of the 5th annual congress of the cognitive science society, Rochester

    Google Scholar 

  • Hinton GE, Sejnowski TJ (1983b) Optimal perceptual inference. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE Computer Society, Washington DC, pp 448–453

    Google Scholar 

  • Kullback S, Leibler RA (1951) On information and sufficiency. Ann Math Stat 22(1):79–86

    Article  Google Scholar 

  • van Kampen NG (1990) Stochastic processes in physics and chemistry. North-Holland, Amsterdam

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute “Carlos I” for Theoretical and Computational Physics and Department of Electromagnetism and Matter Physics, Facultad de Ciencias, Universidad de Granada, Granada, Spain

    Joaquin J. Torres

Authors
  1. Joaquin J. Torres
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Joaquin J. Torres .

Editor information

Editors and Affiliations

  1. Atlanta, Georgia, USA

    Dieter Jaeger

  2. Department of Biomedical Engineering, Florida International University, Miami, Florida, USA

    Ranu Jung

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer Science+Business Media New York

About this entry

Cite this entry

Torres, J.J. (2014). Boltzmann Machine. In: Jaeger, D., Jung, R. (eds) Encyclopedia of Computational Neuroscience. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-7320-6_676-1

Download citation

  • DOI: https://doi.org/10.1007/978-1-4614-7320-6_676-1

  • Received:

  • Accepted:

  • Published:

  • Publisher Name: Springer, New York, NY

  • Online ISBN: 978-1-4614-7320-6

  • eBook Packages: Springer Reference Biomedicine and Life SciencesReference Module Biomedical and Life Sciences

Publish with us

Policies and ethics

Chapter history

  1. Latest

    Boltzmann Machine
    Published:
    19 December 2019

    DOI: https://doi.org/10.1007/978-1-4614-7320-6_676-2

  2. Original

    Boltzmann Machine
    Published:
    24 February 2014

    DOI: https://doi.org/10.1007/978-1-4614-7320-6_676-1

Search

Navigation