Search research articles

Search research articles

Related Experiment Videos

Associative List Memory.

¹School of Engineering, University of Sussex, Falmer, Brighton BN1 9QT, UK

Neural Networks : the Official Journal of the International Neural Network Society

|August 1, 1997

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 journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026

Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026

See all related 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

This study presents Associative List Memory (ALM), a novel system for efficient data processing. ALM offers high recall fidelity with low resource needs, making it ideal for large-scale unsupervised learning and noise reduction in databases.

Area of Science:

Computer Science
Artificial Intelligence
Machine Learning

Background:

Traditional memory systems often require significant processing and memory resources.
Sparse Distributed Memory (SDM) offers comparable performance but with different learning and memory structures.
Efficient data processing is crucial for large databases and space-bound applications.

Purpose of the Study:

Introduce Associative List Memory (ALM) with high recall fidelity and low resource requirements.
Demonstrate ALM's suitability for unsupervised class discovery in large datasets.
Highlight ALM's potential for noise reduction and efficient data handling in various computing environments.

Main Methods:

Developed a novel Associative List Memory (ALM) architecture.

Related Experiment Videos

Implemented ALM for unsupervised learning of noisy patterns.

Utilized ALM in a recall mode for noise removal and pattern assignment.

Main Results:

ALM achieves high recall fidelity with minimal memory and processing demands.
Demonstrated unsupervised learning of 1000-bit patterns with over 30% noise.
Achieved effective noise removal, restoring original patterns with high accuracy.
Processing times are practical for personal computer database applications.

Conclusions:

Associative List Memory (ALM) provides a viable, efficient alternative to existing memory systems.
ALM is well-suited for unsupervised data analysis, pattern recognition, and noise reduction.
ALM's low resource requirements make it suitable for both personal computers and space-bound microprocessors, potentially reducing data transmission rates.