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 Video

Updated: Jul 7, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Handwritten digit recognition by adaptive-subspace self-organizing map (ASSOM).

B Zhang¹, M Fu, H Yan

¹Department of Electrical and Computer Engineering, University of Newcastle, NSW 2308, Australia.

IEEE Transactions on Neural Networks

|February 7, 2008

Summary

We introduce a novel neural network approach for the adaptive-subspace self-organizing map (ASSOM) for handwritten digit recognition. This method achieves high accuracy, demonstrating its effectiveness in pattern classification tasks.

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

[Technique of implanting 17 alpha-methyltestosterone to induce the sex reversal of Epinephelus malabaricus].

Ying yong sheng tai xue bao = The journal of applied ecology·2002

Same author

[Effect of different source iron on piglet's growth, metabolism and environment].

Ying yong sheng tai xue bao = The journal of applied ecology·2002

Same author

[Factors affecting colonization of introduced microorganisms on plant roots].

Ying yong sheng tai xue bao = The journal of applied ecology·2002

Same author

[Gastric evacuation rate of black sea bream(Sparus macrocephalus)].

Ying yong sheng tai xue bao = The journal of applied ecology·2002

Same author

[Assimilation efficiency of pacific oyster Crassortrea gigas].

Ying yong sheng tai xue bao = The journal of applied ecology·2002

Same author

[Correction of nasal deformity in unilateral cleft lip of adult cases].

Zhonghua zheng xing wai ke za zhi = Zhonghua zhengxing waike zazhi = Chinese journal of plastic surgery·2002

Area of Science:

Artificial Intelligence
Machine Learning
Neural Networks

Background:

The adaptive-subspace self-organizing map (ASSOM) is an advanced technique in self-organizing map (SOM) computation.
Existing methods for ASSOM implementation may face challenges with numerical stability.

Purpose of the Study:

To propose a numerically stable method for realizing ASSOM using nonlinear autoencoder networks.
To apply the developed ASSOM model to a modular handwritten digit recognition system.

Main Methods:

Implementation of ASSOM via a neural learning algorithm within nonlinear autoencoder networks.
Development of a modular classification system using ten ASSOM modules, each dedicated to a digit class.
Classification based on comparing reconstruction errors from each module.

More Related Videos

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

Published on: January 5, 2024

Related Experiment Videos

Last Updated: Jul 7, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

Image Recognition and Parameter Analysis of Concrete Vibration State Based on Support Vector Machine

Published on: January 5, 2024

Main Results:

The proposed ASSOM method demonstrates numerical stability.
The modular classification system achieved 99.3% accuracy on the training set.
The system attained over 97% classification accuracy on the testing set for handwritten digits.

Conclusions:

The neural learning algorithm effectively realizes ASSOM with enhanced numerical stability.
The modular ASSOM system is a promising approach for handwritten digit recognition.
The method shows high classification accuracy even with relatively small module sizes.