101–110 of 111 posts
Maybe an NN for Sudoku should use AlphaGo type of architecture.
Earlier quoted context omitted.
I just feel bad about this "my intuition is that you'll need more layers than 10 in the NN, and much much more data." I still find current AI as basically a filter. Image to text, speech to text e.tc A smart AI would be able to figure out sudoku rules from a very small sample of games, it would then figure out a rudimentary backtracking algorithm. It would then sleep over it and figure out more patterns like naked si…
When a pig suddenly starts to dance the remarkable thing is not that it can not do a tango, but that it can dance at all.
I don't think optimizing a rats nest of functions with SGD is that impressive. If a model lacks explanatory power what use is it to people?
In this case when the solution from the NN is incorrect what recourse do you have? The actual solution might be an arbitrary permutation of what the NN gave you and there is no way to tell which rows and columns will have to be reshuffled to get the actual solution or even if there is a solution. The constraints might be inconsistent and you will never know.
Earlier quoted context omitted.
Yeah, yeah, sudoku is easy for computers. That's not the point. The point is learning about neural networks. So yeah, "adding a neural net" does help with that.
In which case the hard part is finding a suitable problem; you might be better off learning about SMT solvers because you don't have Marc Cuban telling everybody to do it.
Nail, meet hammer.
You can solve sudoku with a SAT solver. You don't need neural networks, this was an assignment in cs 251 at UIC.
SAT - Satisfiability https://en.wikipedia.org/wiki/Boolean_satisfiability_problem Acronyms are always a pet peeve of mine. I would know what a SAT is - since I've spent more than 50% of my life with Computer Science. However, not many people would understand the acronym you'd use. So, it would be great if in general one mentions what SAT refers to rather than using the acronym. Mention the long form the first time an…
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" Universal approximation theory suggest that for a significant class of problems, the answer to this is "obviously" [1]. The problem that remains is how effective is the learning. 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 case…
Earlier quoted context omitted.
There are no easy way to solve SAT as the size of sudoku. Modern day SAT solvers are very large and contains years of experience, containing 10s of heuristics and complex structures. If we can simplify using neural network, I think it's a great step.
Reasonably modern SAT solvers (Say MiniSAT) have a lot less complexity than a modern neural network. Also, I set as a intro to C practical writing a SAT solver which can easily solve any real-world Sudoku instance.
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" Universal approximation theory suggest that for a significant class of problems, the answer to this is "obviously" [1]. The problem that remains is how effective is the learning. 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 case…
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.