Using smaller root than power?

[Make42]

In fcm_get_u you have the line inv_distances = np.reciprocal(nonzero_distances) ** (1 / (m - 1)). Shouldn't m-1 be replaced with m? In fcm you write um = u ** m afterall.

[99991]

I think there was some issue with literature where m was used differently depending on author. Not sure though if this was the exact issue.

The derivation went something like this. The -1 in the computation of u comes from taking the derivative with respect to u. When computing v, there is no derivative with respect to u, so no -1 there.

But maybe there is a mistake in there somewhere, so if you find any, feel free to point them out.