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

Neural associative memory storing gray-coded gray-scale images.

G Costantini¹, D Casali, R Perfetti

¹Dept. of Electron. Eng., Univ. of Rome "Tor Vergata", Italy.

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

Abnormal arm swing movements in Parkinson's disease: onset, progression and response to L-Dopa.

Journal of neuroengineering and rehabilitation·2025

Same author

Antiproton annihilation at rest in thin solid targets and comparison with Monte Carlo simulations.

The European physical journal. A, Hadrons and nuclei·2024

Same author

Does F<sub>4</sub>TCNQ Adsorption on Cu(111) Form a 2D-MOF?

The journal of physical chemistry. C, Nanomaterials and interfaces·2023

Same author

First Measurement of Hard Exclusive π^{-}Δ^{++} Electroproduction Beam-Spin Asymmetries off the Proton.

Physical review letters·2023

Same author

First CLAS12 Measurement of Deeply Virtual Compton Scattering Beam-Spin Asymmetries in the Extended Valence Region.

Physical review letters·2023

Same author

Nuclear magnetic resonance signal decay in the presence of a background gradient: Normal and anomalous diffusion.

The Journal of chemical physics·2023

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 neural associative memory for storing grayscale images using binary neural networks. The method efficiently stores and recalls images via parallel computation, offering stability and cost-effectiveness.

Area of Science:

Artificial Intelligence
Computer Science
Neuroscience

Background:

Traditional associative memories face challenges in storing complex data like grayscale images efficiently.
Binary neural networks offer a computationally efficient framework for memory tasks.

Purpose of the Study:

To develop a neural associative memory capable of storing and recalling grayscale images.
To leverage binary neural networks for efficient image storage and retrieval.

Main Methods:

Decomposition of grayscale images into binary representations using gray-coding.
Storage of binary images in brain-state-in-a-box (BSB) type binary neural networks.
Implementation of parallel computation for both learning and recall processes.

Related Experiment Videos

Main Results:

The proposed method demonstrates effective storage and recall of grayscale images.
The learning algorithm ensures asymptotic stability of stored patterns with low computational cost.
Parallel computation significantly reduces processing time for learning and recall.

Conclusions:

The presented neural associative memory offers an effective and efficient solution for grayscale image storage.
The approach utilizing binary neural networks and parallel computation is promising for future memory systems.
The method provides control over weight precision and guarantees pattern stability.