In machine learning, the trade-off between bias and variance is crucial for achieving good generalization.

曾经尝试过，曾经失败过。没关系。再试一次。再失败一次。失败得更好。

不要害怕失败，因为失败是成功的垫脚石。

A good mathematician is lazy, but in a constructive way.

每次我写一本书，每次我面对那张空白页，我都确信我做不到。

文学毫无用处，正因如此它不可或缺。