1
The sample size should be on the first axis. i.e.
$X.shape = (m, n_x) $
$Y.shape = (m, 1) $
You can simply transpose the data.
1
It is possible. Creating higher resolution imaging with deep learning has been done in several fields. Medical imaging is one of the most common fields.
The general approach is called "learning-based upsampling". It is also called "resolution enhancement" or "super-resolution (SR) reconstruction" in the literature. The goal is ...
1
There's no standard range of values because evaluation scores are never good or bad in absolute, they are relevant with respect to a reference. The standard way to report evaluation scores in a paper is to present them in the context of other methods for the same task:
If there are other results about the same task (or a similar task) in the literature, ...
Only top voted, non community-wiki answers of a minimum length are eligible
