Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Learning in higher order Boltzmann machines using linear response.

M A Leisink1, H J Kappen

  • 1Department of Biophysics, University of Nijmegen, The Netherlands. www.mbfys.kun.nl/martijn.

Neural Networks : the Official Journal of the International Neural Network Society
|August 11, 2000
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Minimal navigation solution for a swarm of tiny flying robots to explore an unknown environment.

Science robotics·2020
Same author

Path integral control and state-dependent feedback.

Physical review. E, Statistical, nonlinear, and soft matter physics·2015
Same author

Adaptive multiclass classification for brain computer interfaces.

Neural computation·2014
Same author

Adaptive classification on brain-computer interfaces using reinforcement signals.

Neural computation·2012
Same author

On the use of interaction error potentials for adaptive brain computer interfaces.

Neural networks : the official journal of the International Neural Network Society·2011
Same author

Competition between synaptic depression and facilitation in attractor neural networks.

Neural computation·2007
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

We developed an efficient method for higher-order Boltzmann machines using mean field theory and linear response correction. This approximation works well for learning and inference, especially when network couplings are not excessively strong.

Area of Science:

  • Computational neuroscience
  • Machine learning
  • Statistical physics

Background:

  • Higher-order Boltzmann machines are complex models requiring efficient learning and inference methods.
  • Existing methods may struggle with the computational demands of higher-order interactions.

Purpose of the Study:

  • To present an efficient method for learning and inference in higher-order Boltzmann machines.
  • To evaluate the accuracy and performance of the proposed method against exact calculations.
  • To demonstrate the applicability of the method to a benchmark problem.

Main Methods:

  • The proposed method utilizes mean field theory augmented with a linear response correction.
  • Correlations were computed using both the exact method and the approximation for a third-order network.

Related Experiment Videos

  • The performance was assessed by comparing learning algorithms and solving the shifter problem.

    • Main Results:

    • The linear response approximation provides accurate results for correlations in higher-order Boltzmann machines.
    • The method successfully solves the shifter problem, demonstrating practical utility.
    • Accuracy is maintained when network couplings remain within a moderate range.

    Conclusions:

    • The linear response approximation offers an efficient and effective approach for higher-order Boltzmann machines.
    • The method's validity is confirmed for learning, inference, and problem-solving tasks.
    • Careful consideration of coupling strengths is advised for optimal performance.