Not necessarily, sometimes dimensionality reduction (the more common terminology used, for what is basically compression) is the explicit goal.
Can be used for outlier detection, similarity search, etc.
During training, you find a projection of the input, for example an image, to a smaller space, and then back to the original image. This is referred to as encoding and decoding. The error fuction would be a measure of how similar the in- and output images are.
AI does work like that.
With (variational) auto-encoders, it's very explicit.
With shallow convolutional neural networks, it's fun to visualize the trained kernel weights, as they often return an abstract, to me dreamlike, representations of the thing being trained for. Although derived through a different method, search for "eigenfaces" as an example of what I mean.
In the recent hype model architecture, attention and transformers, the encoded state can be thought of as a compressed version of it's input. But human interpretation of those values is challenging.
Is it an albini or a species?
I've seen bright IR emittors, that can oversaturate some cameras
It's tough. You are not alone.
Is that a problem?
I'm self employed.
Found out I'm depressed, decided to reduce work to 3 days a week.
Raised prices to reduce clients. Turns out I now make more, doing less work. It is what it is.
It's not an elementary question.
Best I can guess is: plenty of people, plenty of reasons. Which is a stupid answer.
Thank you for the suggestion. I'll look into that
I don't know what that is. Please, tell me all about it
It took me 30 years to learn that change is possible