Why 'deep learning' (sort of) works

Discovered: Oct 14, 2020.Why “deep learning” (sort of) works “At that time, I still more or less believed what I’d learned at M.I.T. in the 1970s era of classical AI, which saw pattern recognition as applied logic. The basic idea was to recognize all the relevant traits, and then apply an Aristotelian taxonomy to make the classification. But I’d found, along with everyone else, that this didn’t really work, among other things because it’s at least as hard to recognize the relevant traits as to recognize the final category.”