Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network

Tamura, Hiroshi

doi:https://doi.org/10.1038/s41598-024-84981-1

Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network

Tamura, Hiroshi

Scientific Reports, 2025, 15, 67

Number of Access:236（2025-08-16 20:13 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/99632

Link to primary information

File	Format	Terms of use	Size	Views	Date.Available	Description	information
SciRep_15_67	pdf	None	4.61 MB	24	2025.01.17

Creative Commons : Attribution - NonCommercial - NoDerivatives

Item Information

Output File Export EndNote Basic Export Mendeley

Title	Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network
Creator	NRID 1000080304038 1000080304038 researchmap permalink read0191175 read0191175 Scopus Author ID 55458238900 55458238900 CreatorName Tamura, Hiroshi
Description	Tamura H. Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network. Scientific Reports 15, 67 (2025); https://doi.org/10.1038/s41598-024-84981-1.
Abstract	Functional modular organization is observed in a variety of cortical areas in the brain. In the visual cortex of primates, adjacent neurons often respond to the same visual submodality, such as color or orientation, and have a similar preferred orientation or preferred color. However, it remains unclear why functional modular organization emerges in the cerebral cortex. In the present study, I constructed and trained a multistream convolutional neural network to examine whether filters in the same stream acquire similar properties. Although filters in the same stream were able to develop any structures, they acquired similar degrees of orientation and color selectivity and preferred similar orientations and colors. The deletion of filters in a single stream that had similar degrees of stimulus selectivity resulted in larger decreases in classification accuracy than the deletion of those that did not. By contrast, the deletion of filters in a single stream that shared a preferred stimulus resulted in similar decreases in classification accuracy to the deletion of those that did not. Together, these findings suggest that filters with similar degrees of stimulus selectivity in the same stream are required for optimal task performance of the multistream convolutional neural network, and probably of the brain.
Publisher	Nature Research
Source Title	Scientific Reports
Volume (Issue)	15
Page	67
Date of Issued	2025-01-02
Language	English
Handle URL	https://hdl.handle.net/11094/99632
eISSN	20452322
Relation.isSupplementTo	DOI (Publisher Version) https://doi.org/10.60574/96433
Relation.isIdenticalTo	DOI (Publisher Version) https://doi.org/10.1038/s41598-024-84981-1
Access Rights	open access
CopyRight	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
oaire:version	Version of Record
Category	学術雑誌論文 Journal Article

Resource Type	journal article
Local Type	Journal Article
DCTERMS.bibliographicCitation	Scientific Reports. 2025, 15, p. 67
DC.title	Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network
DC.creator	Tamura, Hiroshi
DC.publisher	Nature Research
DC.language' scheme='DCTERMS.RFC1766	English
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-01-02
DC.identifier	https://doi.org/10.1038/s41598-024-84981-1
DC.identifier	https://doi.org/10.60574/96433
DC.description	Tamura H. Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network. Scientific Reports 15, 67 (2025); https://doi.org/10.1038/s41598-024-84981-1.
DCTERMS.abstract	Functional modular organization is observed in a variety of cortical areas in the brain. In the visual cortex of primates, adjacent neurons often respond to the same visual submodality, such as color or orientation, and have a similar preferred orientation or preferred color. However, it remains unclear why functional modular organization emerges in the cerebral cortex. In the present study, I constructed and trained a multistream convolutional neural network to examine whether filters in the same stream acquire similar properties. Although filters in the same stream were able to develop any structures, they acquired similar degrees of orientation and color selectivity and preferred similar orientations and colors. The deletion of filters in a single stream that had similar degrees of stimulus selectivity resulted in larger decreases in classification accuracy than the deletion of those that did not. By contrast, the deletion of filters in a single stream that shared a preferred stimulus resulted in similar decreases in classification accuracy to the deletion of those that did not. Together, these findings suggest that filters with similar degrees of stimulus selectivity in the same stream are required for optimal task performance of the multistream convolutional neural network, and probably of the brain.
DC.rights	This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
DC.format	99632
citation_title	Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network
citation_author	Tamura, Hiroshi
citation_publisher	Nature Research
citation_language	English
citation_date	2025-01-02
citation_journal_title	Scientific Reports
citation_volume	15
citation_firstpage	67
citation_doi	https://doi.org/10.1038/s41598-024-84981-1
citation_doi	https://doi.org/10.60574/96433
citation_public_url	https://hdl.handle.net/11094/99632

Acquisition of similar properties by filters in the same stream of a multistream convolutional neural network

Link to primary information

Item Information

Show details