![]()
0. Referencehttps://proceedings.mlr.press/v9/glorot10a.html Understanding the difficulty of training deep feedforward neural networksWhereas before 2006 it appears that deep multi-layer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with experimental resul...proceedings.mlr.press1. Introduction- 본 논문은 Xavier Initialization..
![]()
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...
![]()
0. Referencehttps://arxiv.org/abs/1512.03385 Deep Residual Learning for Image RecognitionDeeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions witharxiv.org1. Introduction- 해당 논문은 "더 성능이 좋은 Network를 만..
![]()
0. Referencehttps://arxiv.org/abs/1906.02629 When Does Label Smoothing Help?The generalization and learning speed of a multi-class neural network can often be significantly improved by using soft targets that are a weighted average of the hard targets and the uniform distribution over labels. Smoothing the labels in this way prevearxiv.org1. Introduction- Classification,Speech recognition, Machi..
