Neural network, how to normalize data such as time?

Question

Neural networks

Hello, please tell me how to normalize enum type data, let's say time or colors, when there are many options, 24 hours a day, or 60 minutes an hour, etc.
In one article it was said that when there are enumerations, then you can issue them as several parameters, i.e. let's say day or night, then we pass 2 parameters day and night and pass 0 and 1 or 1 and 0, but here, as I have already written, there are much more options.
Who can say anything about this?

Answer 1

In binary form, wouldn't it work?
Like 12 minutes = 1100 minutes

Answer 2

Projection onto a circle, for example.

def make_harmonic_features(value, period=24):
    value *= 2 * np.pi / period 
    return np.cos(value), np.sin(value)

https://medium.com/open-machine-learning-course/op...