François Chollet@fchollet · XAI 摘要
曲线拟合是在记录某个生成程序输出的有损近似。符号学习则是在无损地逆向工程该生成程序的源代码。
With curve-fitting， you are recording a lossy approximation of the output of some generative program. With symbolic learning， you are losslessly reverse-engineering the source code of the generative program.
Symbolic learning won't be the best fit for all problems， but for the ones where the latent program is reasonably simple， it will outperform by many orders of magnitude.