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 single-iteration threshold Hamming network.

I Meilijson¹, E Ruppin, M Sipper

¹Sch. of Math. Sci., Tel Aviv Univ.

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

The molecular cartography of malignant and benign sebaceous tumours.

Nature communications·2025

Same author

Tumor and blood B-cell abundance outperforms established immune checkpoint blockade response prediction signatures in head and neck cancer.

Annals of oncology : official journal of the European Society for Medical Oncology·2024

Same author

The tumour microenvironment shapes innate lymphoid cells in patients with hepatocellular carcinoma.

Gut·2021

Same author

The effects of telomere shortening on cancer cells: a network model of proteomic and microRNA analysis.

Genomics·2014

Same author

Common and specific signatures of gene expression and protein-protein interactions in autoimmune diseases.

Genes and immunity·2012

Same author

A systems level strategy for analyzing the cell death network: implication in exploring the apoptosis/autophagy connection.

Cell death and differentiation·2010

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

We introduce a simplified Hamming network that uses a threshold function instead of a complex activation function. This enhanced threshold Hamming network efficiently classifies distorted binary patterns in one step, even with exponentially many memories.

Area of Science:

Computational neuroscience
Machine learning
Pattern recognition

Background:

The original Hamming network is a type of recurrent neural network used for associative memory and pattern classification.
Its performance can be computationally intensive due to the complexity of its activation function and 'winner-take-all' subnet.

Purpose of the Study:

To analyze and improve the performance of the Hamming network for classifying distorted binary patterns.
To simplify the Hamming network architecture and reduce its computational complexity.

Main Methods:

Detailed performance analysis of the Hamming network.
Replacement of the original activation function with a simple threshold function.
Elimination of the 'winner-take-all' subnet by optimizing the threshold value.

Related Experiment Videos

Main Results:

The modified Hamming network, termed the threshold Hamming network, correctly classifies input patterns.
Classification is achieved in a single iteration.
High accuracy is maintained even when the number of stored patterns grows exponentially with pattern length.

Conclusions:

The threshold Hamming network offers a computationally efficient alternative to the original Hamming network.
This simplified architecture maintains high classification accuracy, making it suitable for large-scale pattern recognition tasks.