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

Structured Pyramidal Neural Networks.

Alessandra M Soares1, Bruno J T Fernandes1, Carmelo J A Bastos-Filho1

  • 11 ECOMP, Polytechnic School of Pernambuco, University of Pernambuco, Recife, Pernambuco 50720-001, Brazil.

International Journal of Neural Systems
|April 1, 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

Comparing Social Robot Embodiment for Child Musical Education.

Journal of intelligent & robotic systems·2022
Same author

Using a Support Vector Machine Based Decision Stage to Improve the Fault Diagnosis on Gearboxes.

Computational intelligence and neuroscience·2019
Same author

Height and Weight Estimation From Anthropometric Measurements Using Machine Learning Regressions.

IEEE journal of translational engineering in health and medicine·2018
Same author

HAGR-D: A Novel Approach for Gesture Recognition with Depth Maps.

Sensors (Basel, Switzerland)·2015
Same author

Constructive autoassociative neural network for facial recognition.

PloS one·2014
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

Structured Pyramidal Neural Networks (SPNN) offer adaptive receptive fields and fewer parameters than original Pyramidal Neural Networks (PNN). SPNN achieves competitive performance with reduced computational resources.

Area of Science:

  • Computer Vision
  • Deep Learning
  • Artificial Intelligence

Background:

  • Pyramidal Neural Networks (PNN) are inspired by the human visual system and deep learning.
  • PNNs utilize receptive fields for computer vision tasks.
  • Existing PNN models have limitations in adaptability and parameter tuning.

Purpose of the Study:

  • To introduce a novel variation of PNN called Structured Pyramidal Neural Network (SPNN).
  • To address limitations of original PNNs regarding fixed receptive field sizes and numerous parameters.
  • To improve computational efficiency and model applicability.

Main Methods:

  • Developed SPNN with self-adaptive variable receptive fields.
  • Employed Delaunay Triangulation and k-means clustering for structure determination.
Keywords:
Delaunay triangulationPyramidal neural networksclusteringreceptive fields

Related Experiment Videos

  • Compared SPNN performance against PNN, Convolutional Neural Network (CNN), and Support Vector Machine (SVM).

    • Main Results:

    • SPNN demonstrated superior results compared to original PNNs.
    • SPNN achieved performance comparable to CNN and SVM.
    • SPNN utilized lower memory capacity and processing time than existing models.

    Conclusions:

    • SPNN offers a more flexible and efficient alternative to traditional PNNs.
    • The novel structure determination method enhances model adaptability.
    • SPNN presents a promising approach for computer vision applications requiring efficient resource utilization.