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

Cubic approximation neural network for multivariate functions.

D Stein1, A Feuer

  • 1Department of Management Engineering, Technion-Israel Institute of Technology, Haifa, Israel.

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 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

Factors affecting small dental business in rural Germany: Evidence from Hessen.

Community dental health·2024
Same author

Quantitative biomarkers for liver metastases: comparison of MRI diffusion-weighted imaging heterogeneity index and fluorine-18-fluoro-deoxyglucose standardised uptake value in hybrid PET/MR.

Clinical radiology·2018
Same author

High-fructose diet during adolescent development increases neuroinflammation and depressive-like behavior without exacerbating outcomes after stroke.

Brain, behavior, and immunity·2018
Same author

The effect of P38 MAP kinase inhibition in a mouse model of influenza.

Journal of medical microbiology·2018
Same author

Safety of Anti-TNF Treatment in Liver Transplant Recipients: A Systematic Review and Meta-analysis.

Journal of Crohn's & colitis·2017
Same author

Effects of Intranasal Oxytocin on the Interpretation and Expression of Emotions in Anorexia Nervosa.

Journal of neuroendocrinology·2017
Same journal

A practical design of backdoor trigger under frequency-based orthogonality constraints.

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

EEG fine-grained visual semantic decoding via a multimodal framework.

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

Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems.

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

Theoretical analysis of the denoising autoencoder using Tweedie's formula.

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

Frequency-based cross-attention fusion network for RGB-D salient object detection.

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

HTNet: A self-supervised heterogeneous triple network for multi-modal data.

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

This study presents the Cubic Approximation Neural Network (CANN), a novel architecture for approximating multivariate functions. CANN allows for calculating network size based on error bounds but faces challenges with high-dimensional inputs.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Local approximation networks are widely used for function approximation.
  • Challenges exist in determining network size and analyzing learning performance for these networks.

Purpose of the Study:

  • Introduce a novel neural network architecture, the Cubic Approximation Neural Network (CANN).
  • Enable quantitative evaluation of approximation capabilities and analysis of learning processes.
  • Address the trade-offs in learning rate and steady-state performance.

Main Methods:

  • Developed a new neural network architecture: Cubic Approximation Neural Network (CANN).
  • Implemented methods for quantitative evaluation of approximation capabilities based on desired error bounds.

Related Experiment Videos

  • Analyzed the learning process performance, including the trade-off between learning rate and steady-state performance.

    • Main Results:

    • CANN demonstrates simplicity in concept and structure.
    • Quantitative evaluation of approximation capabilities is possible, allowing calculation of network size for a given error bound.
    • The trade-off between learning rate and steady-state performance is clearly demonstrated during training.

    Conclusions:

    • CANN offers a simple yet effective approach to local approximation of multivariate functions.
    • The architecture allows for predictable network sizing based on error tolerance.
    • A known limitation is the exponential growth in neuron count with input vector dimensionality, common to local approximation networks.