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

Stability in contractive nonlinear neural networks.

D G Kelly1

  • 1Department of Mathematics, University of North Carolina, Chapel Hill 27599.

IEEE Transactions on Bio-Medical Engineering
|March 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

Novel pressurized solvent extraction vessels for the analysis of polychlorinated biphenyl congeners in avian whole blood.

Analytica chimica acta·2010
Same author

Audit of suspected chronic intestinal pseudo-obstruction in patients with gynecologic cancer.

European journal of gynaecological oncology·2009
Same author

Should patients with a pre-operative prostate-specific antigen greater than 15 ng/ml be offered radical prostatectomy?

Irish journal of medical science·2005
Same author

Urinary tract fistulas following gynaecological surgery.

Journal of obstetrics and gynaecology : the journal of the Institute of Obstetrics and Gynaecology·2004
Same author

An open trial of octreotide long-acting release in the management of short bowel syndrome.

The American journal of gastroenterology·2001
Same author

Frequency and site-dependent variations in vibration detection thresholds on the face.

Somatosensory & motor research·2000
Same journal

Enhancing Volumetric Imaging in Linear-Array Photoacoustic Tomography: multiview fusion with deep learning.

IEEE transactions on bio-medical engineering·2026
Same journal

Robust Rule-based Heuristic Assistance Strategy for a Semi-Active Shoulder Exoskeleton Used in Overhead Work.

IEEE transactions on bio-medical engineering·2026
Same journal

Highly Accelerated 1-mm Isotropic 3D Chemical Exchange Saturation Transfer MRI Using Wave-Co-CAIPI at 5 Tesla.

IEEE transactions on bio-medical engineering·2026
Same journal

Systematic Evaluation of Hip Exoskeleton Assistance Parameters for Enhancing Gait Stability During Ground Slip Perturbations.

IEEE transactions on bio-medical engineering·2026
Same journal

SleepConFormer: A Single-Channel EEG Framework for Sleep Staging and Consciousness Assessment in Patients with Disorders of Consciousness.

IEEE transactions on bio-medical engineering·2026
Same journal

Modeling Partial and Total Support of Left Ventricular Assist Device for Discrete Hemodynamic Control Framework.

IEEE transactions on bio-medical engineering·2026
See all related articles

This study introduces a neural network model where synaptic weights ensure stable encoding, making the network

Area of Science:

  • Computational neuroscience
  • Mathematical modeling of neural networks

Background:

  • Neural networks exhibit complex electrical activity patterns.
  • Understanding the stability and response characteristics of neural networks is crucial.

Purpose of the Study:

  • To analyze a neural network model of the form mu chi = -x + p + WF(x).
  • To establish conditions for stable network equilibrium and state-independent responses.
  • To explore the relationship between synaptic weights, network dynamics, and frequency characteristics.

Main Methods:

  • Mathematical analysis of the contraction mapping principle applied to WF(x).
  • Investigation of eigenvalue properties of synaptic weight matrices (W).
  • Utilizing Fourier transforms for spatially-homogeneous synaptic weight analysis.

Related Experiment Videos

Main Results:

  • A unique, globally asymptotically stable equilibrium is achieved when WF(x) is a contraction.
  • Mild restrictions on W and F(x) guarantee network stability.
  • Eigenvalues of W relate to the Fourier transform of connection patterns in linear, homogeneous cases.

Conclusions:

  • The model demonstrates stable encoding properties, independent of initial network states.
  • Synaptic weight patterns can be constructed to match desired frequency characteristics of cortical activity.
  • Relationships between the nonlinear model and its linear approximation are established in spatial and frequency domains.