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

Complex-valued multistate neural associative memory.

S Jankowski¹, A Lozowski, J M Zurada

¹Inst. of Electron. Fundamentals, Warsaw Univ. of Technol.

IEEE Transactions on Neural Networks

|January 1, 1996

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

Haematology and critical care - new bedfellows?

Anaesthesia·2016

Same author

STAT6 and STAT1 are essential antagonistic regulators of cell survival in classical Hodgkin lymphoma cell line.

Leukemia·2009

Same author

The use of neuromuscular blockers to facilitate mechanical ventilation in severe asthma.

British journal of hospital medicine (London, England : 2005)·2009

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

Blind extraction of singularly mixed source signals.

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

A new multivalued associative memory model using complex-valued neurons can store and recall grayscale images. This advanced neural network generalizes the Hopfield network, offering enhanced memory capabilities.

Area of Science:

Computational neuroscience
Artificial intelligence
Complex systems

Background:

Associative memory models are crucial for artificial intelligence.
Existing models like the Hopfield network have limitations in storing complex data.
Multivalued and complex-valued neurons offer potential for enhanced memory capacity.

Purpose of the Study:

To introduce a novel multivalued associative memory model.
To demonstrate its capability in storing and recalling grayscale images.
To establish its relationship with existing neural network models.

Main Methods:

Developed a fully connected attractor neural network model.
Utilized multistate complex-valued neurons.
Introduced and evaluated a computational energy function to prove stability.

Related Experiment Videos

Estimated storage capacity based on neuron states.

Main Results:

The proposed model successfully stores and recalls grayscale images.
The complex-valued neural network is a generalization of the Hopfield network.
Network stability is proven for asynchronous dynamics using the energy function.
Storage capacity is estimated in relation to the number of accessible neuron states.

Conclusions:

The multivalued associative memory model offers a powerful new approach for image storage and retrieval.
This complex-valued neural network architecture provides a significant advancement over traditional models.
The model demonstrates theoretical stability and offers insights into storage capacity limitations.