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
- 저널정보
- 한국통계학회 CSAM(Communications for Statistical Applications and Methods) CSAM(Communications for Statistical Applications and Methods) 제26권 제6호
- 발행연도
- 2019.11
- 수록면
- 591 - 610 (20page)
이용수
초록· 키워드
오류제보하기
Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.
목차
Abstract
1. Introduction
2. Deep learning procedures and basics of CNN
3. Advanced techniques for training DNN
4. Convolutional neural network case study: MNIST and CIFAR10 dataset
5. Conclusion
References
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
CNN 인공지능을 이용한 서울 지역의 PM10 예측 모델 개발
한국기상학회 학술대회 논문집
2018 .10
-
Beginner's guide to neural networks for the MNIST dataset using MATLAB
한국수학논문집
2018 .01
-
Temporal Interpolation of Numerical Model Using 3D Convolutional Neural Network
한국기상학회 학술대회 논문집
2022 .05
-
딥러닝을 이용한 장기 파랑예측 가능성 연구
한국연안방재학회지
2020 .01
-
Convolutional Neural Network (CNN)을 이용한 엘니뇨 예측
한국기상학회 학술대회 논문집
2017 .10
-
Tutorial and applications of convolutional neural network models in image classification
한국데이터정보과학회지
2022 .05
-
A review and comparison of convolution neural network models under a unified framework
CSAM(Communications for Statistical Applications and Methods)
2022 .03
-
Understanding recurrent neural network for texts using English-Korean corpora
CSAM(Communications for Statistical Applications and Methods)
2020 .05
-
딥 러닝과 KSTAR 초전도 자석
물리학과 첨단기술
2022 .04
-
An Analysis of Plant Diseases Identification Based on Deep Learning Methods
The Plant Pathology Journal
2023 .08
-
Classification of bearded seals signal based on convolutional neural network
극지연구소 초록집
2023 .07
-
Applying Batch Normalization to the MNIST Dataset
Quantitative Bio-Science
2023 .11
-
작물분류에서 기계학습 및 딥러닝 알고리즘의 분류 성능 평가: 하이퍼파라미터와 훈련자료 크기의 영향 분석
대한원격탐사학회지
2018 .01
-
Is it possible to forecast KOSPI direction using deep learning methods?
CSAM(Communications for Statistical Applications and Methods)
2021 .07
-
Arctic Oscillation Index Forecasting Using Convolutional Neural Network
한국기상학회 학술대회 논문집
2022 .10
-
Recent deep learning methods for tabular data
CSAM(Communications for Statistical Applications and Methods)
2023 .03
-
Two-stage Deep Learning Model with LSTM-based Autoencoder and CNN for Crop Classification Using Multi-temporal Remote Sensing Images
대한원격탐사학회지
2021 .08
-
Deformable convolutional network를 기반으로 한 Mask R-CNN
한국데이터정보과학회지
2020 .11
-
Development of a Daily PM10 and PM2.5 Prediction System Based on Deep Long Short-term Memory Neural Network
한국대기환경학회 학술대회논문집
2020 .10
-
Convolutional Neural Network을 이용한 엘니뇨 예측 시스템 개발
한국기상학회 학술대회 논문집
2017 .05
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2023-310-001441744