메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색

논문 기본 정보

자료유형
학위논문
저자정보

유영우 (포항공과대학교, 포항공과대학교 일반대학원)

지도교수
오세영
발행연도
2016
저작권
포항공과대학교 논문은 저작권에 의해 보호받습니다.

이용수0

표지
AI에게 요청하기
추천
검색

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
This thesis presents a fast method to train CNN classifiers through extreme learning and its classification and detection performance is verified with the popular datasets on classification and pedestrian detection. CNN has been one of the best classifiers for images and object recognition. However, the Backpropagation (BP) algorithm, mostly used for training CNN, suffers from slow learning, local minimum, and poor generalization from overfitting. To solve these problems, a new architecture called CNN-ELM has been proposed here. It is based on a local image version of the ELM representation learning. Using MATLAB 2015a, the classification experiments show a comparable or mostly better classification performance compared to the BP trained CNN, with its training speed up to 200 times faster for MNIST, NORB, and CIFAR-10 datasets. The pedestrian detection experiment using INRIA and POSTECH datasets also exhibits much faster training but with similar detection performance than the BP trained CNN.

목차

I. Introduction 1
1.1 Convolutional Neural Network (CNN) 1
1.2 Extreme Learning Machine (ELM) 3
1.3 Thesis Organization 5
II. CNN-ELM Classifier 6
2.1 Architecture of CNN-ELM 6
2.2 Training CNN-ELM 7
2.2.1 Training ELM 7
2.2.2 Training ELM Auto-encoder 9
2.2.3 Training Multi layered ELM 10
2.2.4 Training CNN-ELM 12
2.3 ELM Parallel Learning 16
2.3.1 Memory Issues of Training CNN-ELM 16
2.3.2 Parallel Learning of ELM 16
2.3.3 Parallel Learning of CNN-ELM 18
III. Implementation 19
3.1 Image Classification 20
3.1.1 MNIST DB 20
3.1.2 NORB DB 21
3.1.2 CIFAR-10 DB 22
3.2 Pedestrian detection 22
3.2.1 Detection Method 23
3.3.2 INRIA Pedestrian DB 25
3.3.3 POSTECH Pedestrian DB 27
IV. Experimental Results 29
4.1 Image Classification 29
4.1.1 MNIST DB 29
4.1.2 NORB DB 31
4.1.3 CIFAR-10 DB 32
4.2 Pedestrian Detection 33
4.2.1 INRIA DB 33
4.2.2 POSTECH DB 40
V. Conclusion and Future Works 44
REFERENCES 46

최근 본 자료

전체보기

댓글(0)

0