#论文 《Deep Residual Learning for Image Recognition》
2015年的paper,微软何凯明等。解决的问题:梯度消失/爆炸问题;之前的解决方案:Thisproblem,however,hasbeenlargelyaddressedbynormalizedinitial-ization[23,9,37,13]andintermediatenormalizationlayers[16],whichenablenetworkswithtensoflayerst