Deep neural networks with Elastic Rectified Linear Units for object recognition

@article{Jiang2018DeepNN,
  title={Deep neural networks with Elastic Rectified Linear Units for object recognition},
  author={Xiaoheng Jiang and Yanwei Pang and Xuelong Li and Jing Pan and Yinghong Xie},
  journal={Neurocomputing},
  year={2018},
  volume={275},
  pages={1132-1139}
}
Rectified Linear Unit (ReLU) is crucial to the recent success of deep neural networks (DNNs). In this paper, we propose a novel Elastic Rectified Linear Unit (EReLU) that focuses on processing the positive part of input. Unlike previous variants of ReLU that typically adopt linear or piecewise linear functions to represent the positive part, EReLU is… CONTINUE READING