Question

In what percentage should training and test datashould be divided

Answer 1

$\color{violet}{ \boxed{ \ \huge{ \underline{thaks \: for \: asking \: this \: question}}}}$

$\bold{ \huge{answer}}$
$\bold{ \small{30 \: percentage}}$
$\bold{ \small{should \: training \: and \: test \: data \: should \: be \: divided}}$

Because, although you get a very good accuracy, it does not mean that your trained ANN is a generalized one (If your ANN is not generalized, you will get bizarre outputs for some inputs which were not observed with the training set .

$\bold{ \huge{30}}$
$\bold{ \huge{ \boxed{be \: brainly}}}$

Answer 2

Answer:

Because, although you get a very good accuracy, it does not mean that your trained ANN is a generalized one (If your ANN is not generalized, you will get bizarre outputs for some inputs which were not observed with the training set .