지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2023.4
- 수록면
- 102 - 109 (8page)
- DOI
- 10.5607/en23004
이용수
초록· 키워드
오류제보하기
Connectome, the complete wiring diagram of the nervous system of an organism, is the biological substrate of the mind. While biological neuralnetworks are crucial to the understanding of neural computation mechanisms, recent artificial neural networks (ANNs) have been developedindependently from the study of real neural networks. Computational scientists are searching for various ANN architectures to improve machinelearning since the architectures are associated with the accuracy of ANNs. A recent study used the hermaphrodite Caenorhabditis elegans (C. elegans) connectome for image classification tasks, where the edge directions were changed to construct a directed acyclic graph (DAG). In this study,we used the whole-animal connectomes of C. elegans hermaphrodite and male to construct a DAG that preserves the chief information flow in theconnectomes and trained them for image classification of MNIST and fashion-MNIST datasets. The connectome-inspired neural networks exhibitedover 99.5% and 92.6% of accuracy for MNIST and fashion-MNIST datasets, respectively, which increased from the previous study. Together,we conclude that realistic biological neural networks provide the basis of a plausible ANN architecture. This study suggests that biological networkscan provide new inspiration to improve artificial intelligences (AIs).
목차
등록된 정보가 없습니다.
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Neural : Future
International Digital Design Invitation Exhibition
2021 .08
-
Towards Diversity: Neural Architecture Search with Diverse Structure
한국콘텐츠학회 ICCC 논문집
2020 .11
-
고정밀 이미지 분류기를 위한 엣지 강화 신경망
한국지식정보기술학회 논문지
2020 .01
-
Deep Neural Network Structure Design for Equipment Failure Prediction in Smart Factory
아시아태평양융합연구교류논문지
2021 .12
-
Exploring the Possibility of Motor Imagery Classification using Artificial Neural Networks: An EEG study
한국HCI학회 학술대회
2023 .02
-
Classification of Fishing Operation Pattern Using Deep Neural Network
한국콘텐츠학회 ICCC 논문집
2018 .12
-
Development of artificial intelligence-based network analysis technology
한국콘텐츠학회 ICCC 논문집
2021 .12
-
Comparison of Weight Initialization Techniques for Deep Neural Networks
The International journal of advanced culture technology
2019 .01
-
Content based Similar Image Retrieval Method using Deep Neural Network
한국콘텐츠학회 ICCC 논문집
2021 .12
-
Mobility Modes Classification Method using Convolution Neural Network
한국콘텐츠학회 ICCC 논문집
2019 .12
-
COVID-19 patients classification using Graph neural network on a Heterogeneous graph
한국콘텐츠학회 ICCC 논문집
2020 .11
-
Artificial Intelligence
International Digital Design Invitation Exhibition
2020 .11
-
artificial intelligence
한국콘텐츠학회 ICCC 논문집
2020 .11
-
Artificial Intelligence
International Digital Design Invitation Exhibition
2018 .05
-
A.I.(Artificial Intelligence)
International Digital Design Invitation Exhibition
2016 .05
-
Artificial Intelligence
International Digital Design Invitation Exhibition
2016 .05
-
artificial intelligence
International Digital Design Invitation Exhibition
2020 .11
-
Product Name Identification from Documents using Artificial Neural Networks
한국콘텐츠학회 ICCC 논문집
2015 .12
-
신경망 학습에서 프라이버시 이슈 및 대응방법 분석
디지털융복합연구
2019 .01
-
Categorizing Ship’s Speed Data for Applying Artificial Neural Network in Harbour Area
한국콘텐츠학회 ICCC 논문집
2017 .12
이 논문의 저자 정보
최근 본 자료
댓글(0)
0