FReLU: Flexible Rectified Linear Units for Improving Convolutional Neural Networks
| Autor: | Xiangmin Xu, Bolun Cai, Suo Qiu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
FOS: Computer and information sciences
Contextual image classification Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Activation function Computer Science - Computer Vision and Pattern Recognition 020207 software engineering 02 engineering and technology Rectifier (neural networks) Residual Convolutional neural network Backpropagation 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business Algorithm |
| Zdroj: | ICPR |
| DOI: | 10.1109/icpr.2018.8546022 |
| Popis: | Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks. However, because of the zero-hard rectification, ReLU networks miss the benefits from negative values. In this paper, we propose a novel activation function called \emph{flexible rectified linear unit (FReLU)} to further explore the effects of negative values. By redesigning the rectified point of ReLU as a learnable parameter, FReLU expands the states of the activation output. When the network is successfully trained, FReLU tends to converge to a negative value, which improves the expressiveness and thus the performance. Furthermore, FReLU is designed to be simple and effective without exponential functions to maintain low cost computation. For being able to easily used in various network architectures, FReLU does not rely on strict assumptions by self-adaption. We evaluate FReLU on three standard image classification datasets, including CIFAR-10, CIFAR-100, and ImageNet. Experimental results show that the proposed method achieves fast convergence and higher performances on both plain and residual networks. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|