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 new design method for the complex-valued multistate Hopfield associative memory.

M K Muezzinoglu¹, C Guzelis, J M Zurada

¹Dept. of Electr. Eng., Louisville Univ., KY, USA.

IEEE Transactions on Neural Networks

|February 2, 2008

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

Determining the bistability parameter ranges of artificially induced lac operon using the root locus method.

Computers in biology and medicine·2015

Same author

Neural networks and hybrid intelligent models: foundations, theory, and applications.

IEEE transactions on neural networks·2008

Same author

A dynamical system perspective of structural learning with forgetting.

IEEE transactions on neural networks·2008

Same author

Analysis of input-output clustering for determining centers of RBFN.

IEEE transactions on neural networks·2008

Same author

Blind extraction of singularly mixed source signals.

IEEE transactions on neural networks·2008

Same author

Nonlinear blind source separation using a radial basis function network.

IEEE transactions on neural networks·2008

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 method for storing integral memory sets in complex-valued multistate Hopfield networks. The technique ensures patterns become local minima, enhancing image reconstruction from noisy data.

Area of Science:

Computational Neuroscience
Artificial Neural Networks
Information Theory

Background:

Hopfield networks are fundamental models for associative memory.
Storing complex, integral memory sets in neural networks presents significant challenges.
Existing methods often struggle with capacity and stability for multistate systems.

Purpose of the Study:

To introduce a novel method for embedding integral memory sets into complex-valued multistate Hopfield networks.
To ensure each memory pattern corresponds to a strict local minimum of the network's energy landscape.
To evaluate the capacity and performance of this method, particularly for image reconstruction.

Main Methods:

Developing a method based on a system of inequalities to define the network's synaptic weights.

Related Experiment Videos

Designing a recurrent network of n multistate neurons with complex, symmetric synaptic weights.

Utilizing a quadratic energy functional that the network aims to minimize.

Conducting computer experiments to determine the maximum number of embeddable integral vectors.

Testing the network's performance on reconstructing noisy gray-scale images.

Main Results:

Each memory pattern is successfully rendered as a strict local minimum of the energy landscape.
The network operates on a finite state space {1,2,...,K}/sup n/ to minimize the quadratic functional.
Computer experiments provide insights into the maximum storage capacity of the network.
The proposed method demonstrates effectiveness in reconstructing noisy gray-scale images.

Conclusions:

The introduced method provides a robust way to store integral memory sets in complex-valued multistate Hopfield networks.
The network architecture and weight setting ensure stable storage and retrieval of memory patterns.
The findings suggest potential applications in pattern recognition and image processing, especially under noisy conditions.