Question

Is this known as a fact or from some analysis that the MNIST data-set is almost as if its sampled from some low (~10?) dimensional manifold? Is there a locally linear embedding to a low-dimensional space? Of course I don't expect the data will be exactly on some low dimensional manifold; there will be some noise.

No correct solution

Licensed under: CC-BY-SA with attribution
Not affiliated with cs.stackexchange
scroll top