I took a grad level course on data mining/machine learning back in the early 2010s, before the current gold rush, and while there was some level of theory and programming, the professor spent a lot of his time discussing these finer points. The (apocryphal) example of armoring planes in the wrong spots [0] sticks with me to this day.
It’s human nature to focus on the more immediate, tangible outcomes - eg going through a pytorch tutorial - over spending time trying to really understand the problem they are trying to solve. Great teachers try to guide their students there, and great students are perpetually calling themselves out mentally to try and stay on the track of understanding rather than rote repetition. But it’s very hard.
It’s human nature to focus on the more immediate, tangible outcomes - eg going through a pytorch tutorial - over spending time trying to really understand the problem they are trying to solve. Great teachers try to guide their students there, and great students are perpetually calling themselves out mentally to try and stay on the track of understanding rather than rote repetition. But it’s very hard.
[0]: http://www.ams.org/publicoutreach/feature-column/fc-2016-06