The Author Online Book Forums are Moving

The Author Online Book Forums will soon redirect to Manning's liveBook and liveVideo. All book forum content will migrate to liveBook's discussion forum and all video forum content will migrate to liveVideo. Log in to liveBook or liveVideo with your Manning credentials to join the discussion!

Thank you for your engagement in the AoF over the years! We look forward to offering you a more enhanced forum experience.

DVD (1) [Avatar] Offline

I've just read about the digit recognizer classifier and I have a question about the choice of the distance used.

I've heard about "Curse of dimensionality" and that Euclidean distance was not a good choice with too many features.
So I would like to know what's the biggest number a features so that Euclidean (or Manhattan) distance is OK.

And I am also interested in the number of examples I have to gather (to be able to learn something) if I have so many features.

I think it would be great to include a little something about this in the book (?)