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
- 2025.3
- 수록면
- 147 - 154 (8page)
- DOI
- 10.5392/IJoC.2025.21.1.147
이용수
초록· 키워드
오류제보하기
The EBP (Error Back-Propagation) Algorithm was initially proposed for training MLP’s (Multi- Layer Perceptrons) and is now widely used for training deep neural networks. This supervised learning algorithm minimizes the error function between the actual output values of MLP’s and their desired values.
However, ICA (Independent Component Analysis) is an unsupervised learning algorithm that aims to maximize the independence among the outputs of neural networks. ICA has been shown to realize visual features in the V1 layer of the human brain by learning from natural scenes and cochlear features of the human ear by learning from auditory signals. In this paper, we propose merging the supervised EBP algorithm with the unsupervised ICA algorithm to enhance the performance of neural networks by training independent features in the initial learning stage. This approach mirrors the feature-learning process observed in mammals during the early stages of life. Furthermore, the proposed approach is verified through simulations on isolated-word recognition tasks, achieving improved classification performance with faster learning convergence. In detail, when the number of hidden nodes is 100, EBP with ICA reaches a misclassification ratio of 2.78% on the test data at 160 epochs, while EBP achieves 3.28% at 300 epochs.
However, ICA (Independent Component Analysis) is an unsupervised learning algorithm that aims to maximize the independence among the outputs of neural networks. ICA has been shown to realize visual features in the V1 layer of the human brain by learning from natural scenes and cochlear features of the human ear by learning from auditory signals. In this paper, we propose merging the supervised EBP algorithm with the unsupervised ICA algorithm to enhance the performance of neural networks by training independent features in the initial learning stage. This approach mirrors the feature-learning process observed in mammals during the early stages of life. Furthermore, the proposed approach is verified through simulations on isolated-word recognition tasks, achieving improved classification performance with faster learning convergence. In detail, when the number of hidden nodes is 100, EBP with ICA reaches a misclassification ratio of 2.78% on the test data at 160 epochs, while EBP achieves 3.28% at 300 epochs.
목차
Abstract
1. Introduction
2. Integration of Error Back-Propagation and Independent Component Analysis Algorithms
3. Simulations
4. Conclusions
References
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Unsupervised feature learning for classification
한국컴퓨터정보학회 학술발표논문집
2016 .07
-
딥러닝을 이용한 트러스 구조물의 정적 및 동적 거동 예측
한국공간구조학회지
2018 .01
-
초공동 시험체 초기 개략정렬 및 오차분석
제어로봇시스템학회 논문지
2022 .06
-
Molecular Analysis of C/EBPβ and C/EBPδ Genes and Their Role After Exercise in Thoroughbred Horses
동물자원연구
2018 .01
-
Review on the Recent Welding Research with Application of CNN-Based Deep Learning Part I: Models and Applications
대한용접·접합학회지
2021 .02
-
딥러닝의 모형과 응용사례
지능정보연구
2016 .06
-
ICA가 청각 상상 뇌파 분류에 미치는 영향
한국정보기술학회논문지
2025 .03
-
Self-Supervised Learning through Ad Hoc Pretext Tasks: Survey
대한전자공학회 학술대회
2021 .06
-
Method for the Initial Value of Weights to Obtain Stable Results of Unsupervised Neural Network
Proceedings of The International Workshop on Future Technology
2019 .01
-
Application of artificial neural network technique to predict polarization curves of stainless steels with various factors
한국표면공학회 학술발표회 초록집
2021 .06
-
A Novel Face Recognition Algorithm based on the Deep Convolution Neural Network and Key Points Detection Jointed Local Binary Pattern Methodology
Journal of Electrical Engineering & Technology
2017 .01
-
차량 내 Permutation 문제 해결을 위한 마이크 어레이 빔포밍 ICA 방식
정보 및 제어 논문집
2021 .04
-
Comparison of Deep Learning Algorithms Based on Face Recognition
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2015 .06
-
Improvement of the Convergence Rate of Deep Learning by Using Scaling Method
International journal of advanced smart convergence
2017 .01
-
Unsupervised 3D Shape Classification Using Graph Neural Networks
한국통신학회 학술대회논문집
2023 .02
-
Straightforward Clarification for Fundamental Algorithms of Artificial Neural Networks
IEIE Transactions on Smart Processing & Computing
2023 .06
-
ICAS 2022 참관기
항공우주매거진
2022 .11
-
딥 러닝 피쳐를 통한 영상 정합 기술
대한전자공학회 학술대회
2016 .06
-
Neuron-specific expression of p48 Ebp1 during murine brain development and its contribution to CNS axon regeneration
BMB Reports
2017 .01
-
Fully self-supervised learning for regression problems
한국방송미디어공학회 학술발표대회 논문집
2024 .06
이 논문의 저자 정보
최근 본 자료
댓글(0)
0