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

The Bifurcating Neuron network 1.

G Lee1, N H Farhat

  • 1Electrical Engineering Department, University of Pennsylvania, Philadelphia 19104, USA.

Neural Networks : the Official Journal of the International Neural Network Society
|February 24, 2001
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

Characterization of the 5' flanking region of the rat D(3) dopamine receptor gene.

Journal of neurochemistry·2001
Same author

An unusual case of duplex ureteropyelocystoplasty.

Scandinavian journal of urology and nephrology·2001
Same author

A newly uncovered phenotype associated with the fruitless gene of Drosophila melanogaster: aggression-like head interactions between mutant males.

Behavior genetics·2001
Same author

Abnormalities of male-specific FRU protein and serotonin expression in the CNS of fruitless mutants in Drosophila.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2001
Same author

Newly diagnosed pulmonary sarcoidosis in HIV-infected patients.

Radiology·2001
Same author

The inflammatory response within Dukes' B colorectal cancers: implications for progression of micrometastases and patient survival.

The American journal of gastroenterology·2001
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

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

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

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

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

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

Researchers developed a Bifurcating Neuron (BN) network, a chaotic neural network, demonstrating superior associative memory capabilities compared to traditional models. This novel network design overcomes limitations like spurious states, offering biologically plausible characteristics.

Area of Science:

  • Computational Neuroscience
  • Artificial Neural Networks
  • Chaos Theory

Background:

  • The Bifurcating Neuron (BN) is a model of a neuron incorporating environmental modulation.
  • It is mathematically equivalent to the sine-circle map, a one-dimensional map.

Purpose of the Study:

  • To leverage the mathematical properties of the BN and sine-circle map for neural network design.
  • To investigate symmetry in the BN for bistability control and associative memory.
  • To design and evaluate a novel chaotic pulse-coupled neural network.

Main Methods:

  • Mathematical analysis of the Bifurcating Neuron and its equivalence to the sine-circle map.
  • Exploration of symmetry properties to induce bistability via attractor-merging crisis.
  • Introduction of sinusoidal fluctuation to control bistability.

Related Experiment Videos

  • Design and numerical simulation of the Bifurcating Neuron Network 1 (BNN-1).

    • Main Results:

    • The BN exhibits controllable bistability through attractor-merging crisis and sinusoidal threshold modulation.
    • The Bifurcating Neuron Network 1 (BNN-1) was successfully designed as a chaotic pulse-coupled neural network.
    • BNN-1 demonstrated superior performance over continuous-time Hopfield networks in mitigating the spurious-minima problem.
    • BNN-1 exhibited several biologically plausible characteristics.

    Conclusions:

    • The mathematical framework of one-dimensional maps can be effectively applied to design complex neural networks.
    • The Bifurcating Neuron Network 1 (BNN-1) presents a promising alternative for associative memory with enhanced performance and biological plausibility.