원문정보
한국인터넷방송통신학회
The International Journal of Advanced Smart Convergence
Volume 6 Number 4
2017.12
pp.73-79
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
The Convolutional Neural Network (CNN) has shown an excellent performance in computer vision task. Applications of CNN include image classification, object detection in images, autonomous driving, etc. This paper will evaluate the performance of CNN model with ReLU and SELU as activation function. The evaluation will be performed on four different choices of hyperparameter which are initialization method, network configuration, optimization technique, and regularization. We did experiment on each choice of hyperparameter and show how it influences the network convergence and test accuracy. In this experiment, we also discover performance improvement when using SELU as activation function over ReLU.
목차
Abstract
1. Introduction
2. Activation function
3. Experiments
3.1 Initialization method
3.2 Network configuration
3.3 Optimization techniques
3.4 Regularization
4. Conclusion
Acknowledgement
References
1. Introduction
2. Activation function
3. Experiments
3.1 Initialization method
3.2 Network configuration
3.3 Optimization techniques
3.4 Regularization
4. Conclusion
Acknowledgement
References
저자정보
참고문헌
자료제공 : 네이버학술정보