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

Multilayer feedforward networks with adaptive spline activation function.

S Guarnieri1, F Piazza, A Uncini

  • 1Dipartimento di Elettronica e Automatica, Università di Ancona, Italy, 60131 Ancona, Italy.

IEEE Transactions on Neural Networks
|February 7, 2008
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

Evidence for the Collective Nature of Radial Flow in Pb+Pb Collisions with the ATLAS Detector.

Physical review letters·2026
Same author

Evidence for the Dimuon Decay of the Higgs Boson in pp Collisions with the ATLAS Detector.

Physical review letters·2025
Same author

Evidence for Longitudinally Polarized W Bosons in the Electroweak Production of Same-Sign W Boson Pairs in Association with Two Jets in pp Collisions at sqrt[s]=13  TeV with the ATLAS Detector.

Physical review letters·2025
Same author

Observation of tt[over ¯] Production in Pb+Pb Collisions at sqrt[s_{NN}]=5.02  TeV with the ATLAS Detector.

Physical review letters·2025
Same author

Low-Energy Excitations in Bosonic Quantum Quasicrystals.

Physical review letters·2025
Same author

Search for Dark Matter Produced in Association with a Dark Higgs Boson in the bb[over ¯] Final State Using pp Collisions at sqrt[s]=13  TeV with the ATLAS Detector.

Physical review letters·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
Same journal

Data-based identification and control of nonlinear systems via piecewise affine approximation.

IEEE transactions on neural networks·2011
Same journal

Data-core-based fuzzy min-max neural network for pattern classification.

IEEE transactions on neural networks·2011
See all related articles

A novel adaptive spline activation function neural network (ASNN) offers high representation capabilities for efficient real-time pattern recognition and data processing. This new neural network design improves generalization and learning speed using a Catmull-Rom cubic spline.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Traditional neural networks often require complex structures for high performance.
  • Efficient real-time processing for pattern recognition and data tasks remains a challenge.

Purpose of the Study:

  • To introduce a new adaptive spline activation function neural network (ASNN).
  • To leverage high representation capabilities for simplified network architectures.
  • To enhance real-time problem-solving in pattern recognition and data processing.

Main Methods:

  • Developed an ASNN utilizing a Catmull-Rom cubic spline as the neuron's activation function.
  • Designed a network structure suitable for both software and hardware implementation.
  • Evaluated performance on pattern recognition and data processing tasks.

Related Experiment Videos

Main Results:

  • The ASNN demonstrated high representation capabilities, enabling networks with fewer interconnections.
  • Achieved improvements in generalization capability compared to existing methods.
  • Showcased enhanced learning speed in both pattern recognition and data processing tasks.

Conclusions:

  • The proposed ASNN offers an efficient and simplified approach to neural network design.
  • Catmull-Rom cubic splines provide a robust activation function for practical applications.
  • ASNNs present a promising advancement for real-time AI applications.