Memory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation

Recent achievements on CNN (convolutional neural networks) and DNN (deep neural networks) researches provide a lot of practical applications on computer vision area. However, these approaches require construction of huge size of training data for learning process. This paper tries to find a way for...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Kyuchang Kang, Changseok Bae
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/7f53c8f0b66345fdbda50c48f3ba2abe
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7f53c8f0b66345fdbda50c48f3ba2abe
record_format dspace
spelling oai:doaj.org-article:7f53c8f0b66345fdbda50c48f3ba2abe2021-11-25T16:38:05ZMemory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation10.3390/app1122107862076-3417https://doaj.org/article/7f53c8f0b66345fdbda50c48f3ba2abe2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10786https://doaj.org/toc/2076-3417Recent achievements on CNN (convolutional neural networks) and DNN (deep neural networks) researches provide a lot of practical applications on computer vision area. However, these approaches require construction of huge size of training data for learning process. This paper tries to find a way for continual learning which does not require prior high-cost training data construction by imitating a biological memory model. We employ SDR (sparse distributed representation) for information processing and semantic memory model, which is known as a representation model of firing patterns on neurons in neocortex area. This paper proposes a novel memory model to reflect remembrance of morphological semantics of visual input stimuli. The proposed memory model considers both memory process and recall process separately. First, memory process converts input visual stimuli to sparse distributed representation, and in this process, morphological semantic of input visual stimuli can be preserved. Next, recall process can be considered by comparing sparse distributed representation of new input visual stimulus and remembered sparse distributed representations. Superposition of sparse distributed representation is used to measure similarities. Experimental results using 10,000 images in MNIST (Modified National Institute of Standards and Technology) and Fashion-MNIST data sets show that the sparse distributed representation of the proposed model efficiently keeps morphological semantic of the input visual stimuli.Kyuchang KangChangseok BaeMDPI AGarticlevisual stimulisparse distributed representationmorphological semanticrecallTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10786, p 10786 (2021)
institution DOAJ
collection DOAJ
language EN
topic visual stimuli
sparse distributed representation
morphological semantic
recall
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle visual stimuli
sparse distributed representation
morphological semantic
recall
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Kyuchang Kang
Changseok Bae
Memory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation
description Recent achievements on CNN (convolutional neural networks) and DNN (deep neural networks) researches provide a lot of practical applications on computer vision area. However, these approaches require construction of huge size of training data for learning process. This paper tries to find a way for continual learning which does not require prior high-cost training data construction by imitating a biological memory model. We employ SDR (sparse distributed representation) for information processing and semantic memory model, which is known as a representation model of firing patterns on neurons in neocortex area. This paper proposes a novel memory model to reflect remembrance of morphological semantics of visual input stimuli. The proposed memory model considers both memory process and recall process separately. First, memory process converts input visual stimuli to sparse distributed representation, and in this process, morphological semantic of input visual stimuli can be preserved. Next, recall process can be considered by comparing sparse distributed representation of new input visual stimulus and remembered sparse distributed representations. Superposition of sparse distributed representation is used to measure similarities. Experimental results using 10,000 images in MNIST (Modified National Institute of Standards and Technology) and Fashion-MNIST data sets show that the sparse distributed representation of the proposed model efficiently keeps morphological semantic of the input visual stimuli.
format article
author Kyuchang Kang
Changseok Bae
author_facet Kyuchang Kang
Changseok Bae
author_sort Kyuchang Kang
title Memory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation
title_short Memory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation
title_full Memory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation
title_fullStr Memory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation
title_full_unstemmed Memory Model for Morphological Semantics of Visual Stimuli Using Sparse Distributed Representation
title_sort memory model for morphological semantics of visual stimuli using sparse distributed representation
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/7f53c8f0b66345fdbda50c48f3ba2abe
work_keys_str_mv AT kyuchangkang memorymodelformorphologicalsemanticsofvisualstimuliusingsparsedistributedrepresentation
AT changseokbae memorymodelformorphologicalsemanticsofvisualstimuliusingsparsedistributedrepresentation
_version_ 1718413086690377728