delving deep into rectifiers:surpassing human-level performance on imagenet classification

0. Referencehttps://arxiv.org/abs/1502.01852 Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet ClassificationRectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Rectified Linear Unit (PReLU) that generaarxiv...