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

Pattern-recognition by an artificial network derived from biologic neuronal systems.

D L Alkon1, K T Blackwell, G S Barbour

  • 1Laboratory for Cellular and Molecular Neurobiology, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892.

Biological Cybernetics
|January 1, 1990
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

Heterogenous Distribution of Fluorescent Phorbol Ester Signal in Living Sea Urchin Embryos.

The Biological bulletin·2018
Same author

Calcium: amplitude, duration, or location?

The Biological bulletin·2015
Same author

Calcium-dependent inactivation of calcium channels in the medial striatum increases at eye opening.

Journal of neurophysiology·2015
Same author

Dynamic modulation of spike timing-dependent calcium influx during corticostriatal upstates.

Journal of neurophysiology·2013
Same author

Approaches and tools for modeling signaling pathways and calcium dynamics in neurons.

Journal of neuroscience methods·2013
Same author

PKC activator therapeutic for mild traumatic brain injury in mice.

Neurobiology of disease·2010
Same journal

Harmonic memory in phasor neural networks.

Biological cybernetics·2026
Same journal

Correction: Decreased spinal inhibition leads to undiversified locomotor patterns.

Biological cybernetics·2026
Same journal

Foundational issues of network models in biology.

Biological cybernetics·2026
Same journal

Dynamical mechanisms for coordinating long-term working memory based on the precision of spike-timing in cortical neurons.

Biological cybernetics·2026
Same journal

Distinct dopaminergic spike-timing-dependent plasticity rules are suited to different functional roles.

Biological cybernetics·2026
Same journal

Fluctuation-response relations for a two-stage population of spiking neurons stimulated by common noise.

Biological cybernetics·2026
See all related articles

A novel artificial neural network, DYnamically STable Associative Learning (DYSTAL), learns correlations and anticorrelations for pattern classification and restoration. Its efficient, stable, and flexible design is suitable for hardware implementation.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Artificial neural networks (ANNs) are inspired by biological nervous systems.
  • Existing ANNs often have limitations in computational efficiency, parameter stability, and structural flexibility.
  • There is a need for ANNs that can handle complex learning tasks and are suitable for hardware implementation.

Purpose of the Study:

  • To introduce a novel artificial neural network, DYnamically STable Associative Learning (DYSTAL).
  • To demonstrate the performance of DYSTAL in pattern classification and restoration tasks.
  • To highlight the desirable properties of DYSTAL, including computational efficiency and hardware suitability.

Main Methods:

  • Developed a novel artificial neural network architecture based on neurobiological observations.

Related Experiment Videos

  • Configured the network for pattern classification and restoration by adjusting output units.
  • Trained the network to perform tasks such as the XOR function and pattern restoration from noisy data.

    • Main Results:

    • DYSTAL associatively learns correlations and anticorrelations.
    • Computational complexity scales linearly (O(N)) with the number of connections.
    • Network performance is stable across wide parameter ranges and input field sizes.
    • Large numbers of non-orthogonal patterns can be stored.
    • Network weights can be computed a priori for deterministic patterns.
    • Successfully trained for XOR function and pattern restoration from binary/analog noise.

    Conclusions:

    • DYSTAL offers a computationally efficient and stable learning paradigm.
    • The network's flexibility in structure and learning capabilities make it versatile.
    • DYSTAL's suitability for hardware (VLSI) implementation is a significant advantage.
    • The network advances the field of neurobiologically inspired artificial intelligence.