I don't know much about AI, though I know a bit about ML, statistics and neural nets. And one good way I've found to learn those subjects has been to find interesting papers and then figure out how to replicate/reimplement them.

This might sound a little uninspiring, but it's a solid start, and often you can make improvements over the authors' original stuff -- especially in areas where you may have more experience, e.g. computational efficiency.