The activation function is an important component in Convolutional Neural Networks (CNNs). For instance, recent breakthroughs in Deep Learning can be attributed to the Rectified Linear Unit (ReLU). Another recently proposed activation function, the Exponential Linear Unit (ELU), has the supplementary property of reducing bias shift without explicitly centering the values at zero. In this paper, we show that learning a parameterization of ELU improves its performance. We analyzed our proposed Parametric ELU (PELU) in the context of vanishing gradients and provide a gradient-based optimization framework. We conducted several experiments on CIFAR-10/100 and ImageNet with different network architectures, such as NiN, Overfeat, All-CNN and ResNet. Our results show that our PELU has relative error improvements over ELU of 4.45% and 5.68% on CIFAR-10 and 100, and as much as 7.28% with only 0.0003% parameter increase on ImageNet. We also observed that Vgg using PELU tended to prefer activations saturating closer to zero, as in ReLU, except at the last layer, which saturated near -2. Finally, other presented results suggest that varying the shape of the activations during training along with the other parameters helps controlling vanishing gradients and bias shift, thus facilitating learning.
翻译:激活功能是进化神经网络的一个重要组成部分。 例如, 深学习中最近出现的突破可以归因于校正线条股( ReLU) 。 最近提出的另一个激活功能, 即光学线条股( ELU), 具有减少偏向转变的补充属性, 而没有将数值明确以零为中心。 在本文中, 我们显示, 学习ELU的参数化提高了它的性能。 我们分析了在渐变梯度背景下拟议的参数ELU( PELU) (PELU), 并提供了一个基于梯度的优化框架。 我们在CIFAR- 10/ 100和图像网络上进行了几次实验, 并有不同的网络结构, 如 NiN、 Overfeat、 All- CNN 和 ResNet 。 我们的结果显示, 我们的PELU 相对差差差于ELU 4.45% 和 5. 68% 的, 在 CIFAR- 10 和 100 上, 以及 高达7. 28% 的图像网络上只增加了0.003% 的偏差偏差偏差偏差点, 的偏向接近零的 饱和 图像优化框架。 我们还观察到, 图像LU 图像LU 上倾向于偏向更接近于启动饱和更近零的,,, 渐近于 渐变的 渐变变变的, 因此变变变变变的,, 在 列列 列 列 列 列 列 列 列