Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

A competitive associative memory model and its dynamics.

X W He¹, C P Kwong, Z B Xu

¹Dept. of Inf. Eng., Chinese Univ. of Hong Kong, Shatin.

IEEE Transactions on Neural Networks

|January 1, 1995

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

[Prognostic analysis of local excision in 153 cases of locally advanced low rectal cancer following neoadjuvant therapy].

Zhonghua wei chang wai ke za zhi = Chinese journal of gastrointestinal surgery·2025

Same author

[Advances in the mechanisms of kidney aging and intervention strategies: a research review].

Zhonghua nei ke za zhi·2025

Same author

[Clinical phenotyping of acute aortic dissection patients: a latent class analysis based on a multicenter retrospective cohort study].

Zhonghua xin xue guan bing za zhi·2025

Same author

[Research progress of renal-targeted nanopharmaceuticals in the treatment of acute kidney injury].

Zhonghua nei ke za zhi·2023

Same author

[A case of pulmonary aspergillus infection in underground coal mine workers].

Zhonghua lao dong wei sheng zhi ye bing za zhi = Zhonghua laodong weisheng zhiyebing zazhi = Chinese journal of industrial hygiene and occupational diseases·2023

Same author

[Application of antegrade wire and guide wire-capture technique in transcatheter aortic valve implantation: three cases report].

Zhonghua xin xue guan bing za zhi·2022

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

This study introduces a novel competitive recognition associative memory model. It effectively excludes spurious data points and recalls unique stable states from any initial input, mimicking biological species competition.

Area of Science:

Computational Neuroscience
Artificial Intelligence
Machine Learning

Background:

Conventional associative memory networks utilize noncompetitive or distance-based competitive recognition.
These networks often suffer from spurious equilibrium points, limiting their reliability.

Purpose of the Study:

To introduce a novel competitive recognition associative memory model.
To simulate the competitive persistence observed in biological species.
To exclude spurious equilibrium points and ensure unique stable states.

Main Methods:

Development of a new associative memory model based on competitive recognition.
Mathematical analysis to demonstrate equilibrium point properties.
Investigation of network behavior with varying competitive parameters.

Related Experiment Videos

Main Results:

The proposed model uses only prototype patterns as equilibrium points, eliminating spurious states.
The network exhibits a unique stable equilibrium point for a specific competitive parameter.
This unique stable state is reliably recalled from any initial key.

Conclusions:

The novel competitive recognition model offers improved performance over conventional networks.
It effectively addresses the issue of spurious states in associative memory.
The model's ability to recall unique stable states has significant implications for pattern recognition applications.