开发鲁棒的学习算法需要对底层数据分布有深刻的理解。
The development of robust learning algorithms requires a deep understanding of the underlying data distribution.
People, even more than things, have to be restored, renewed, revived, reclaimed, and redeemed; never throw out anyone.
I think that in mathematics, and maybe in life, you have to be willing to be a little bit lost.