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

Sensitivity Analysis for Probabilistic Neural Network Structure Reduction.

Piotr A Kowalski, Maciej Kusy

    IEEE Transactions on Neural Networks and Learning Systems
    |April 20, 2017
    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

    Non-Destructive Surface Characterization Using Microscopic Imaging and Data Modeling.

    Materials (Basel, Switzerland)·2025
    Same author

    Numerical analysis of factors, pace and intensity of the corona virus (COVID-19) epidemic in Poland.

    Ecological informatics·2021
    Same author

    Prediction of 10-year Overall Survival in Patients with Operable Cervical Cancer using a Probabilistic Neural Network.

    Journal of Cancer·2019
    Same author

    Fuzzy c-means-based architecture reduction of a probabilistic neural network.

    Neural networks : the official journal of the International Neural Network Society·2018
    Same author

    Prediction of 5-year overall survival in cervical cancer patients treated with radical hysterectomy using computational intelligence methods.

    BMC cancer·2017
    Same author

    Interval probabilistic neural network.

    Neural computing & applications·2017
    Same journal

    Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    cPU: Consistent Risk Estimator for Positive-Unlabeled Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

    IEEE transactions on neural networks and learning systems·2026
    See all related articles

    Local sensitivity analysis (LSA) offers an effective method for simplifying probabilistic neural networks (PNNs). This approach reduces network complexity by identifying and removing insignificant input features and redundant neurons, enhancing PNN performance.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computational Neuroscience

    Background:

    • Probabilistic Neural Networks (PNNs) are powerful classification tools but can suffer from structural complexity.
    • Simplifying PNN structures is crucial for improving computational efficiency and potentially enhancing generalization.
    • Existing reduction methods may not fully address the nuances of PNN architecture.

    Purpose of the Study:

    • To introduce and evaluate Local Sensitivity Analysis (LSA) as a novel method for PNN structure simplification.
    • To develop algorithms for PNN reduction focusing on input layer and pattern neuron simplification.
    • To compare the effectiveness of LSA-based reduction against Global Sensitivity Analysis (GSA) and other common methods.

    Main Methods:

    • Development of three algorithms utilizing LSA for PNN reduction: input layer feature selection, pattern neuron removal, and a combined approach.

    Related Experiment Videos

  • Implementation of PNN with a product kernel estimator and one-dimensional Cauchy function, with dimension-wise smoothing parameter calculation.
  • Testing on eight repository datasets using a 10-fold cross-validation procedure to assess classification accuracy.

    • Main Results:

    • LSA effectively reduces PNN structure by selecting significant input features and removing redundant neurons.
    • Reduced PNNs using LSA demonstrate comparable or improved classification quality compared to full-structure PNNs.
    • LSA-based reduction shows competitive performance against GSA and conventional reduction techniques.

    Conclusions:

    • Local Sensitivity Analysis (LSA) is a viable and effective alternative approach for simplifying probabilistic neural network structures.
    • The proposed LSA algorithms provide a systematic way to optimize PNNs for improved efficiency and performance.
    • This study highlights the potential of sensitivity analysis in refining complex machine learning models.