Jove
Visualize
Contact Us

Related Experiment Videos

The Bifurcating Neuron Network 2: an analog associative memory.

Geehyuk Lee1, Nabil H Farhat

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

Neural Networks : the Official Journal of the International Neural Network Society
|April 18, 2002
PubMed
Summary

Researchers designed a Bifurcating Neuron Network (BNN-2) using chaotic neuron models. This network demonstrates associative memory and context-sensitive recall, functioning like volume-holographic memory.

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

Vibrotactile Compliance Feedback for Tangential Force Interaction.

IEEE transactions on haptics·2017
Same author

Self-organization in a parametrically coupled logistic map network: a model for information processing in the visual cortex.

IEEE transactions on neural networks·2009
Same author

Optical realization of bioinspired spiking neurons in the electron trapping material thin film.

Applied optics·2007
Same author

Realization of receptive fields with excitatory and inhibitory responses on equilibrium-state luminescence of electron trapping material.

Optics letters·2007
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

Area of Science:

  • Computational Neuroscience
  • Artificial Neural Networks
  • Chaos Theory

Background:

  • The Bifurcating Neuron (BN) is a chaotic integrate-and-fire neuron model incorporating environmental coherent modulation.
  • The BN's mathematical equivalence to the sine-circle map enables the application of one-dimensional map mathematics to neural network design.

Purpose of the Study:

  • To leverage the BN's properties for designing a novel neural network architecture.
  • To investigate the potential of the BN network for associative memory and context-sensitive information retrieval.

Main Methods:

  • Mathematical analysis of the Bifurcating Neuron's bifurcating diagram.
  • Design and simulation of the Bifurcating Neuron Network 2 (BNN-2), a pulse-coupled neural network.
  • Exploration of the network's dynamical properties and memory recall mechanisms.

Related Experiment Videos

Main Results:

  • The BN functions as an amplitude-to-phase converter and a coincidence detector under specific conditions.
  • The BNN-2 exhibits associative memory for multiple analog patterns.
  • BNN-2 demonstrates volume-holographic memory, switching between memory pages based on coherent modulation frequency, indicating context-sensitive memory.

Conclusions:

  • The Bifurcating Neuron Network (BNN-2) effectively implements associative memory.
  • The network's ability to switch memory pages with changing modulation frequency signifies context-sensitive, holographic-like memory recall.
  • This research opens avenues for advanced neural network designs inspired by chaotic dynamics and environmental modulation.