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

Recognition of general patterns using neural networks.

A J Wong1

  • 1Oak Ridge High School, TN 37830.

Biological Cybernetics
|January 1, 1988
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

Multiscale Assessment of Agricultural Consumptive Water Use in California's Central Valley.

Water resources research·2021
Same author

EGFRvIII gene rearrangement is an early event in glioblastoma tumorigenesis and expression defines a hierarchy modulated by epigenetic mechanisms.

Oncogene·2012
Same author

Immunohistochemical discrimination of wild-type EGFR from EGFRvIII in fixed tumour specimens using anti-EGFR mAbs ICR9 and ICR10.

British journal of cancer·2012
Same author

A novel epidermal growth factor receptor variant lacking multiple domains directly activates transcription and is overexpressed in tumors.

Oncogene·2011
Same author

The role of the c-Jun N-terminal kinase 2-α-isoform in non-small cell lung carcinoma tumorigenesis.

Oncogene·2010
Same author

A variant epidermal growth factor receptor protein is similarly expressed in benign hyperplastic and carcinomatous prostatic tissues in black and white men.

West African journal of medicine·2007
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 new algorithm enables neural networks to recognize general, non-orthogonal patterns, overcoming limitations of the Hopfield model. This advancement allows for teaching complex patterns and improves tolerance for altered or incomplete data.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • The Hopfield model, a neural network, stores memory in symmetric synaptic connections.
  • It is limited to recognizing nearly orthogonal patterns.
  • Recognizing general, non-orthogonal patterns remains a challenge.

Purpose of the Study:

  • To develop a new algorithm for neural network pattern recognition.
  • To enable the recognition of general, non-orthogonal patterns.
  • To extend the capabilities of neural networks beyond the Hopfield model.

Main Methods:

  • A novel algorithm is introduced for constructing the network's memory matrix (Tij).
  • The new memory matrix (Tij) is generally asymmetrical, encompassing the Hopfield network as a special case.

Related Experiment Videos

  • The general form of this class of memory matrices is presented, including the projection matrix neural network as a specific instance.

    • Main Results:

    • The developed algorithm successfully permits the recognition of general, non-orthogonal patterns.
    • Computer modeling demonstrated a neural network utilizing this general memory matrix form successfully recognized non-orthogonal patterns.
    • The new network exhibited tolerance for altered and incomplete data.

    Conclusions:

    • A new method allows neural networks to learn and recognize general patterns, not just orthogonal ones.
    • This extends the library of memory matrices available for neural network pattern recognition.
    • The approach enhances neural network robustness and applicability to complex data recognition tasks.