An Implicit Memory-Based Method for Supervised Pattern Recognition
How the human brain does recognition is still an open question. No physical or biological experiment can fully reveal this process. Psychological evidence is more about describing phenomena and laws than explaining the physiological processes behind them. The need for interpretability is well recogn...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2021-01-01
|
Series: | Discrete Dynamics in Nature and Society |
Online Access: | http://dx.doi.org/10.1155/2021/4472174 |
_version_ | 1798031677254008832 |
---|---|
author | Yu Ma Shafei Wang Junan Yang Yanfei Bao Jian Yang |
author_facet | Yu Ma Shafei Wang Junan Yang Yanfei Bao Jian Yang |
author_sort | Yu Ma |
collection | DOAJ |
description | How the human brain does recognition is still an open question. No physical or biological experiment can fully reveal this process. Psychological evidence is more about describing phenomena and laws than explaining the physiological processes behind them. The need for interpretability is well recognized. This paper proposes a new method for supervised pattern recognition based on the working pattern of implicit memory. The artificial neural network (ANN) is trained to simulate implicit memory. When an input vector is not in the training set, the ANN can treat the input as a “do not care” term. The ANN may output any value when the input is a “do not care” term since the training process needs to use as few neurons as possible. The trained ANN can be expressed as a function to design a pattern recognition algorithm. Using the Mixed National Institute of Standards and Technology database, the experiments show the efficiency of the pattern recognition method. |
first_indexed | 2024-04-11T20:01:18Z |
format | Article |
id | doaj.art-701a2746a7fe49f7a9d9a07ddb53a1a9 |
institution | Directory Open Access Journal |
issn | 1026-0226 1607-887X |
language | English |
last_indexed | 2024-04-11T20:01:18Z |
publishDate | 2021-01-01 |
publisher | Hindawi Limited |
record_format | Article |
series | Discrete Dynamics in Nature and Society |
spelling | doaj.art-701a2746a7fe49f7a9d9a07ddb53a1a92022-12-22T04:05:37ZengHindawi LimitedDiscrete Dynamics in Nature and Society1026-02261607-887X2021-01-01202110.1155/2021/44721744472174An Implicit Memory-Based Method for Supervised Pattern RecognitionYu Ma0Shafei Wang1Junan Yang2Yanfei Bao3Jian Yang4Academy of Military Science of the People’s Liberation Army, Beijing 100000, ChinaAcademy of Military Science of the People’s Liberation Army, Beijing 100000, ChinaInstitution of Electronic Countermeasure, National University of Defense Technology, Hefei 230037, ChinaAcademy of Military Science of the People’s Liberation Army, Beijing 100000, ChinaAcademy of Military Science of the People’s Liberation Army, Beijing 100000, ChinaHow the human brain does recognition is still an open question. No physical or biological experiment can fully reveal this process. Psychological evidence is more about describing phenomena and laws than explaining the physiological processes behind them. The need for interpretability is well recognized. This paper proposes a new method for supervised pattern recognition based on the working pattern of implicit memory. The artificial neural network (ANN) is trained to simulate implicit memory. When an input vector is not in the training set, the ANN can treat the input as a “do not care” term. The ANN may output any value when the input is a “do not care” term since the training process needs to use as few neurons as possible. The trained ANN can be expressed as a function to design a pattern recognition algorithm. Using the Mixed National Institute of Standards and Technology database, the experiments show the efficiency of the pattern recognition method.http://dx.doi.org/10.1155/2021/4472174 |
spellingShingle | Yu Ma Shafei Wang Junan Yang Yanfei Bao Jian Yang An Implicit Memory-Based Method for Supervised Pattern Recognition Discrete Dynamics in Nature and Society |
title | An Implicit Memory-Based Method for Supervised Pattern Recognition |
title_full | An Implicit Memory-Based Method for Supervised Pattern Recognition |
title_fullStr | An Implicit Memory-Based Method for Supervised Pattern Recognition |
title_full_unstemmed | An Implicit Memory-Based Method for Supervised Pattern Recognition |
title_short | An Implicit Memory-Based Method for Supervised Pattern Recognition |
title_sort | implicit memory based method for supervised pattern recognition |
url | http://dx.doi.org/10.1155/2021/4472174 |
work_keys_str_mv | AT yuma animplicitmemorybasedmethodforsupervisedpatternrecognition AT shafeiwang animplicitmemorybasedmethodforsupervisedpatternrecognition AT junanyang animplicitmemorybasedmethodforsupervisedpatternrecognition AT yanfeibao animplicitmemorybasedmethodforsupervisedpatternrecognition AT jianyang animplicitmemorybasedmethodforsupervisedpatternrecognition AT yuma implicitmemorybasedmethodforsupervisedpatternrecognition AT shafeiwang implicitmemorybasedmethodforsupervisedpatternrecognition AT junanyang implicitmemorybasedmethodforsupervisedpatternrecognition AT yanfeibao implicitmemorybasedmethodforsupervisedpatternrecognition AT jianyang implicitmemorybasedmethodforsupervisedpatternrecognition |