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
- 2021.1
- 수록면
- 99 - 107 (9page)
이용수
초록· 키워드
오류제보하기
The important thing in the field of deep learning is to find out the appropriate hyper-parameter for image classification. In this study, the main objective is to investigate the performance of various hyper-parameters in a convolutional neural network model based on the image classification problem. The dataset was obtained from the Kaggle dataset. The experiment was conducted through different hyper-parameters. For this proposal, Stochastic Gradient Descent without momentum (SGD), Adaptive Moment Estimation (Adam), Adagrad, Adamax optimizer, and the number of batch sizes (16, 32, 64, 120), and the number of epochs (50, 100, 150) were considered as hyper-parameters to determine the losses and accuracy of a model. In addition, Binary Cross-entropy Loss Function (BCLF) was used for evaluating the performance of a model. In this study, the VGG16 convolutional neural network was used for image classification. Empirical results demonstrated that a model had minimum losses obtain by Adagrad optimizer in the case of 16 batch sizes and 50 epochs. In addition, the SGD with a 32 batch sizes and 150 epochs and the Adam with a 64 batch sizes and 50 epochs had the best performance based on the loss value during the training process. Interestingly, the accuracy was higher while performing the Adagrad and Adamax optimizer with a 120 batch sizes and 150 epochs. In this study, the Adagrad optimizer with a 120 batch sizes and 150 epochs performed slightly better among those optimizers. In addition, an increasing number of epochs can improve the performance of accuracy. It can help to create a broader scope for further experiments on several datasets to perceive the suitable hyper-parameters for the convolutional neural network. Dataset: https://www.kaggle.com/c/dogs-vs-cats/data
목차
등록된 정보가 없습니다.
참고문헌 (25)
참고문헌 신청
Babanezhad R / 2015 / Stop wasting my gradients:Practical SVRG / J. Adv Neu Info Proc Sys :2251~2259
Bello I / 2017 / Neural optimizer search with reinforcement learning / Int Conf on Machine Learning 1:712~721
Daneshm H / 2016 / Starting small-learning with adaptive sample sizes / Int Conf on Machine Learning 3:2167~2186
Devarakonda A / AdaBatch:Adaptive batch sizes for training deep neural networks
Duchi JC / 2012 / Randomized smoothing for(parallel)stochastic optimization / IEEE Int Conf on Decision and Control 12:5442~5444
Bello I / 2017 / Neural optimizer search with reinforcement learning / Int Conf on Machine Learning 1:712~721
Daneshm H / 2016 / Starting small-learning with adaptive sample sizes / Int Conf on Machine Learning 3:2167~2186
Devarakonda A / AdaBatch:Adaptive batch sizes for training deep neural networks
Duchi JC / 2012 / Randomized smoothing for(parallel)stochastic optimization / IEEE Int Conf on Decision and Control 12:5442~5444
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
SGD, Adam 그리고 중간 optimizer 비교
한국정보과학회 학술발표논문집
2022 .12
-
생산 라인에서의 실시간 배치 크기 결정
산업경영시스템학회지
2019 .01
-
Effects of Hyper-parameters and Dataset on CNN Training
전기전자학회논문지
2018 .03
-
Step-down converter 기반 태양광 모듈용 Optimizer 개발 및 평가
Current Photovoltaic Research
2025 .03
-
기계학습 옵티마이저 성능 평가
전기전자학회논문지
2020 .09
-
DC Offset Removal Based on DNN by Implementing Modified Adam Optimizer
대한전자공학회 학술대회
2022 .06
-
창고시스템에서 분할 배치크기 인출에 대한 저장/인출 차량의 인출소요시간
대한설비관리학회지
2019 .01
-
독립형 에너지 하우스 전력시스템에서의 BIPV용 Optimizer에 대한 연구
전력전자학회 학술대회 논문집
2018 .11
-
Detection of Distracted Driving using Deep Learning
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2021 .02
-
작업완료시각 추정을 활용한 배치 스케줄링 및 사례 연구
산업경영시스템학회지
2020 .01
-
Genetic Algorithms for Batch Loading and Scheduling Problem with Batch Deterioration and Rate-modifying Activities
대한산업공학회 추계학술대회 논문집
2019 .11
-
Performance Comparison of the Optimizers in a Faster R-CNN Model for Object Detection of Metaphase Chromosomes
한국정보통신학회논문지
2019 .11
-
태양광 패널의 최대 전력 발생 시스템을 위한 DC OPTIMIZER 설계
반도체디스플레이기술학회지
2018 .01
-
Breast Masses Evaluation Using Deep Learning for Mammogram Imaging: A Pilot Study
한국통신학회 학술대회논문집
2022 .02
-
Animal Face Classification using Dual Deep Convolutional Neural Network
멀티미디어학회논문지
2020 .04
-
Impact Force Localization and Identification in Structure by Using Optimizer Based on Random Search
한국소음진동공학회 학술대회논문집
2018 .10
-
Performance Analysis of a Power Optimizer for Building-Integrated Photovoltaic (BIPV) Systems in Urban Environments
AFORE
2024 .11
-
A New Approach to Determine Batch Size for the Batch Method in the Monte Carlo Eigenvalue Calculation
Nuclear Engineering and Technology
2019 .01
-
LDA를 활용한 Batch 공정 모니터링 연구의 토픽 모델링 분석
한국산학기술학회 논문지
2022 .04
-
Analysis and Verification of the Stability for PV Series-Connected Power Optimizer System
ICPE(ISPE)논문집
2019 .05
이 논문의 저자 정보
최근 본 자료
댓글(0)
0