- 博客(1)
- 收藏
- 关注
原创 【论文笔记】residual neural network-kaiming he
http://arxiv.org/abs/1512.03385 The stack of layer will cause degradation(same train, more layer, less accuracy, which is not caused by overfit or derivation vanishing). H(x) is expected
2016-03-18 16:41:28
889
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人