Re:Why do CNNs generalize so poorly to small image transform...
by AndrewKemendo on Sunday June 10, 2018 @03:12PM
(#17279692)
test set validation is an overestimate of real-world performance of these systems, but progress on test sets is indicative of progress in real-world settings
I think this is important point to make and talks to the real life limitations of run of the mill SL techniques. If you can't validate with noisy "real world" data, then you're basically staying inside the box and hoping that you've curated well enough to mimic real world conditions.
I still like RL system for the improvement on this, however it's much more difficult in practice.
I think this is important point to make and talks to the real life limitations of run of the mill SL techniques. If you can't validate with noisy "real world" data, then you're basically staying inside the box and hoping that you've curated well enough to mimic real world conditions.
I still like RL system for the improvement on this, however it's much more difficult in practice.