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

Stochastic radial basis functions.

H C Card1

  • 1Department of Electrical and Computer Engineering, University of Manitoba Winnipeg, Manitoba, Canada R3T 5V6. hcard@ee.umanitoba.ca

International Journal of Neural Systems
|November 25, 2003
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

Near IR interband transitions and optical parameters of metal-germanium contacts.

Applied optics·2010
Same author

Photocounting distributions for exponentially decaying sources.

Optics letters·2009
Same author

Doubly stochastic Poisson processes in artificial neural learning.

IEEE transactions on neural networks·2008
Same author

Vector quantization of images using modified adaptive resonance algorithm for hierarchical clustering.

IEEE transactions on neural networks·2008
Same author

Compound binomial processes in neural integration.

IEEE transactions on neural networks·2008
Same author

Gaussian activation functions using Markov chains.

IEEE transactions on neural networks·2008
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

Stochastic signal processing utilizes stochastic counters to approximate Gaussian activation functions for radial basis function networks. This method offers controllable means and variances, enhancing neural network performance.

Area of Science:

  • Computational Neuroscience
  • Signal Processing
  • Artificial Intelligence

Background:

  • Radial basis function networks (RBFNs) are crucial in machine learning.
  • Implementing activation functions efficiently is key to RBFN performance.
  • Stochastic computing offers novel approaches to signal processing.

Purpose of the Study:

  • To investigate the implementation of Gaussian activation functions using stochastic signal processing.
  • To explore the use of stochastic counters for approximating these functions in RBFNs.
  • To analyze the control mechanisms for the statistical properties of the approximated functions.

Main Methods:

  • Utilizing stochastic counters with increment/decrement operations controlled by Bernoulli distributed neural inputs.

Related Experiment Videos

  • Deriving transfer functions relating input/output pulse probabilities.
  • Analyzing the approximation accuracy of Gaussian functions based on the number of counter states.
  • Investigating the control of means and variances via combinational logic functions of binary counter variables.

    • Main Results:

    • Stochastic counters can closely approximate Gaussian activation functions.
    • Approximation accuracy improves with an increased number of states in the stochastic counter.
    • The means and variances of the approximated Gaussian functions are controllable.
    • Bernoulli distributions govern the statistics of neural inputs for counter operations.

    Conclusions:

    • Stochastic signal processing provides a viable method for implementing Gaussian activation functions in RBFNs.
    • The proposed stochastic counter approach offers tunable parameters for neural network design.
    • This method contributes to efficient and potentially hardware-friendly neural network implementations.