对于智能来讲，压缩不是目的，是手段。真正的目的是获取信息从而帮助减少不确定性，而信息的获取量是完全可以被度量的。对于任何一种感兴趣的数据，为了获得最大信息增量的表达（也就是我们常说的记忆或者知识），一个智能系统会努力学习到最有效最高效的压缩算子（例如通过一个神经网络的每一层来实现）。这也就是我常常所说的：我们为了压缩而学习，为了学习而压缩！这也是我的开源新书的主旨。（For intelligence, compression is not the goal. It is a means to an end. The true goal is to gain information that helps reduce uncertainty, which is entirely measurable. For any particular data of interest, to obtain a most informative representation of its distribution (i.e., memory or knowledge), an intelligent system tries to learn the most effective and efficient compressing operations (say layers of a network). Hence the saying: We learn to compress, and we compress to learn!）