컨벌루션 신경망에서 활성 함수가 미치는 영상 분류 성능 비교

목차 (Table of Contents)

• ABSTRACT
• 1. 서론
• 2. 관련 연구
• 3. 학습 데이터베이스 및 실험을 위한 환경 구성
• 4. 실험 결과
• 5. 결론
• REFERENCE

참고문헌 (Reference)

1 정윤주, "딥 컨볼루션 신경망을 이용한 자동차번호판 영역 검출 시스템" 한국멀티미디어학회 20 (20): 1166-1174, 2017

2 S. Zagoruyko, "Wide Residual Networks"

3 K. Jarrett, "What is the Best Multi-stage Architecture for Object Recognition?" 2146-2153, 2009

4 N. Akhtar, "Threat of Adversarial Attacks on Deep Learning in Computer Vision:A Survey"

5 A. L. Maas, "Rectifier Nonlinearities Improve Neural Network Acoustic Models" 2013

6 V. Nair, "Rectified lInear Units Improve Restricted Boltzmann Machines" 807-814, 2010

7 V. Nair, "Rectified Linear Units Improve Restricted Boltzmann Machines" 807-814, 2010

8 I. Sutskever, "On the Importance of Initialization and Momentum in Deep Learning" 28 : 1139-1147, 2013

9 M. Lin, "Network In Network"

10 D. Silver, "Mastering the Game of Go without Human Knowledge" 550 : 354-359, 2017

11 R. Olga, "ImageNet Large ScaleVisual Recognition Challenge" 115 (115): 211-252, 2015

12 K. Alex, "ImageNet Classification with Deep Convolutional Neural Networks" 1097-1105, 2012

13 C. Szegedy, "Going Deeper with Convolutions" 1-9, 2015

14 D. -A. Clevert, "Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)"

15 B. Xu, "Empirical Evaluation of Rectified Activations in Convolutional Network"

16 G. Huang, "Densely Connected Convolutional Networks" 2261-2269, 2017

17 K. He, "Delving Deep Into Rectifiers: Surpassing Human-Level Performance On Imagenet Classification" 1026-1034, 2015

18 L. Yann, "Deep leaning" 521 (521): 436-444, 2015

19 X. Glorot, "Deep Sparse Rectifier Neural Networks" 15 : 315-323, 2011

20 J. Yangqing, "Caffe: An Open Source Convolutional Architecture for Fast Feature Embedding" 675-678, 2014

21 S. loffe, "Batch Normalization:Accelerating Deep Network Training by Reducing Internal Covariate Shift"

22 H. Huang, "Automated Detection and Identification of Blue and Fin Whale Foraging Calls by Combining Pattern Recognition and Machine Learning Techniques" 1-7, 2016