I am still reading Vapnik’s The Nature of Statistical Learning Theory. I began reading it a first time in March, but then left it aside for months, so I started over in October. It’s enlightening and a pleasure to read, if one can stay focused.
Every now and then, Vapnik lets drops of wit fall on the pages, and the reader that can spot them is able to savour the wisdom of a great mind.
I like this one, which was “buried” in a footnote on page 13:
“Of course it is very interesting to know how humans can learn. However, this is not necessarily the best way for creating an artificial learning machine. It has been noted that the study of birds flying was not very useful in constructing the airplane.”
Interesting thought, and nice counterexample. =)
Posted from Providence, Rhode Island, United States.