> Text analysis, reinforcement learning, etc. seem to be areas where deep learning might very well reach a plateau... changing one piece position in a chess game is the difference between a win or loss. These "binary" situations aren't a good match with the assumptions of continuity, differentiablity and such that neural networks depend on.
Deep learning can't do board games like chess and go?!
Wait... are you using pretty darn subtle dry sarcasm to argue that deep learning won't reach a plateau?
I think that markov chain monte carlo is pretty cool even with lightweight playouts. (pick a random move)
The neural net by itself is a "half-baked" chess or go player, it needs the MCMC to be a strong player. (MCMC plus lightweight playouts can beat me at chess if not at go.)
Same with text-analysis, code generation and such. If you can build a hybrid system where the neural net comes up with half-baked answers that can be corrected by a system which is capable of comprehending things like "well-formed" and "valid" then you could be cooking with gas.
What I am seeing though is that people aren't "beginning with the end in mind" the way the Wright Brothers did with flying, rather they are throwing stuff at the wall and seeing what sticks.
Deep learning can't do board games like chess and go?!
Wait... are you using pretty darn subtle dry sarcasm to argue that deep learning won't reach a plateau?