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

A higher order Bayesian neural network with spiking units

A Lansner1, A Holst

  • 1Department of Numerical Analysis and Computing Science, Royal Institute of Technology, Stockholm, Sweden. ala@nada.kth.se

International Journal of Neural Systems
|May 1, 1996
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

Short-term plasticity influences episodic memory recall: an interplay of synaptic traces in a spiking neural network model.

Scientific reports·2025
Same author

Quantification of cefuroxime and flucloxacillin in synovial tissue and bone using ultra-performance convergence chromatography-tandem mass spectrometry.

Journal of chromatography. B, Analytical technologies in the biomedical and life sciences·2024
Same author

Kinetic modelling of serum S100b after traumatic brain injury.

BMC neurology·2016
Same author

Reliability and speed of recall in an associative network.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

The chick embryo yolk-sac blood vessel system as an experimental model for irritation and inflammation.

Toxicology in vitro : an international journal published in association with BIBRA·2010
Same author

Experimental Studies Relating to "Ship-beri-beri" and Scurvy.

The Journal of hygiene·2010
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

We introduce a Bayesian confidence propagation neural network for classification tasks. Higher-order networks overcome limitations of naive Bayesian classifiers, enabling real-world applications like computer diagnostics with uncertain and continuous data.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Science

Background:

  • Naive Bayesian classifiers require independent input attributes, limiting their applicability.
  • Higher-order networks can overcome the independence assumption of naive Bayesian classifiers.

Purpose of the Study:

  • To present a Bayesian confidence propagation neural network for classification.
  • To demonstrate the effectiveness of higher-order networks in overcoming limitations of naive Bayesian classifiers.
  • To adapt the network for real-world tasks involving uncertain and continuous data.

Main Methods:

  • Developed a one-layer Bayesian confidence propagation neural network implementing a naive Bayesian classifier.
  • Extended the network to a higher-order version to handle dependent attributes.

Related Experiment Videos

  • Incorporated stochastic spiking units and soft interval coding for uncertain and continuous inputs.

    • Main Results:

    • The higher-order Bayesian neural network was successfully evaluated on diagnosing a telephone exchange computer.
    • The network demonstrated capability in handling uncertain and continuous valued inputs through specialized units and coding.

    Conclusions:

    • Bayesian confidence propagation neural networks, particularly higher-order variants, offer a robust approach to classification.
    • The developed methods enable the application of Bayesian neural networks to complex, real-world problems with diverse data types.