[scikit-learn] Fwd: Scikit-learn MLPRegressor Help

Gael Varoquaux gael.varoquaux at normalesup.org
Tue Dec 6 06:27:18 EST 2016

On Sat, Dec 03, 2016 at 10:35:03PM +0000, federico vaggi wrote:
> As long as the feature ordering has a meaningful spatial component (as is
> almost always the case when you are dealing with raw pixels as features) CNNs
> will almost always be better. 

There is another important aspect: CNN are meant to work on data that is
translation invariant. Not all images are, for instance not brain images,
because they have been realigned. That said, most images are.


More information about the scikit-learn mailing list