So much missing-the-point in this thread. The point isn't "can we solve sudoku with a completely over-wrought solution", it's "can NN be applied to X class of problems with no human-added domain specific knowledge". And that I think is quite cool.
"can NN be applied to X class of problems with no human-added domain specific knowledge"
I'm not convinced applying them to areas like this one where the are clearly much better approaches teaches us anything useful for more interesting cases, but maybe it does.
[1] NB it's not immediately clear that OPs problem is in that class.
Maybe the useful thing here is that Sudoku is a problem space a lot of people understand pretty well even though it's not trivial. That makes a nice domain for thinking about and understanding NN. I guess that people who are familiar with the problem space of solving Sudoku and similar problems but who don't know much about NN will find this pretty interesting but people who already understand NN pretty well (or aren't familiar with solving puzzles like Sudoku) won't.
It's not obvious.
The problem that remains is how effective is the learning.
To late to add an comment to the original.
I don't think it teaches us much about sudoku, but any formerly 'hard' problem that we've solved using traditional means is perfect for rapidly generating arbitrary amounts of training data, which makes it very useful for learning about neural nets.
(I still think it would fail spectacularly on "super-human" sudokus.)
But why would you care about solving a class of problems with NNs when that class of problems already has much better solutions? Too many new programmers are running to NNs out of pure laziness. NNs are like magic. They solve the problem for you so you don't have to learn how to solve it yourself. Or at least that's the enticing promise.
> NNs are like magic. They solve the problem for you so you don't have to learn how to solve it yourself.
Sounds like you answered your own question; am I missing something?