Each input consists of a $22$ grayscale image.

Represent each pixel value with a single scalar, giving four features

x$1$; x$2$; x$3$; x$4.$

Assume that each image belongs to one among the categories $$square$,$

$$triangle$,$ and $$circle$.$

How to represent the labels?

I Use label encoding.

y $21$; $2$; $3,$ where the integers represent circle; square; triangle respectively.

I Use one$-$hot encoding.

y $2(1$; $0$; $0)$; $(0$; $1$; $0)$; $(0$; $0$; $1).$ y would be a three$-$dimensional vector, with $(1,$

$0,0)$ corresponding to $$circle$,(0,1,0)$ to $$square$,$ and $(0,0,1)$ to $$triangle$.$

Deep Learning