0
$\begingroup$

Let's say I'm working on solving sudoku puzzles with machine learning. Now, plenty of good methods exist for solving sudoku algorithmically, no machine learning required, but let's play along to get to the interesting stuff. I train my model on completed sudoku boards, where the outputs are completed boards, and the inputs are the same boards with most of the squares cleared.

Now mathematically speaking, if you empty enough squares from the board, you'll lose uniqueness in solutions, ending up with multiple possible completed boards resulting from a given input puzzle.

Generating completed sudoku boards is easy, clearing out those boards into puzzles for training is even easier. Figuring out which puzzles no longer have unique solutions is hard. Does it matter?

Can I train my model on my generated dataset, knowing that some of the samples are "non-determinables" where I'm only training on one possible solution out of a few solutions possible for that given board? What effect will this have on training rate and accuracy?

$\endgroup$
1
$\begingroup$

Can I train my model on my generated dataset, knowing that some of the samples are "non-determinables" where I'm only training on one possible solution out of a few solutions possible for that given board?

There are many problems where this or something similar is the case, for example image captioning (some datasets for caption generation, for example COCO, have several captions for each image).

Your example also seems to be more of a structured learning problem (you'd want to navigate problem space locally, not just come up with a solution when you play, because the former variant is most likely intractable).

What effect will this have on training rate and accuracy?

That's a really interesting question, but I think it's too broad - it will depend on the model. For example simple model might have strong assumptions on the noise, and presenting it with many contradictory training samples it might deteriorate severely.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.