Just wanted to know if the value we get by passing, say, random.normal(shape=(3,2)) in the Tensorflow, etc, are normally distributed or if they are randomly chosen from a set of values that are normally distributed? If it's the latter one, then they could be unintentionally belonging to a uniform or any other distribution with some different parameters.
$\begingroup$
$\endgroup$
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
1
TensorFlow's random.normal "outputs random values from a normal distribution".
Values from other distributions are sampled by their respective functions: tf.random.uniform, tf.random.gamm, tf.random.poisson.
answered Feb 8 at 23:28
-
$\begingroup$ But those "random" values could make a non-random set of values for some other distribution. Like you can plot them out. $\endgroup$ Feb 9 at 12:31