[kypro]

I'm not sure I'm following. Uncertainty is really just another way of saying probability. You handle uncertainty with probabilistic approaches which neural networks do.

Or put another way a square explicitly might be four straight lines connected at right angles, but in reality such a perfect shape is never going to exist. What's important is that the system understands that shape which has roughly straight lines and roughly connected and right angles is "squarish" enough to be a labeled a square, and the less "squarish" the shape becomes the less certain the system becomes that square is the correct label. Neural networks certainly achieve this.

We might not always understand what the parameters of a neutral networks are encoding, but that's a limitation of our brains, not of neural networks.

[js8]

Probability is common, but not the only way to model uncertainty. There are also different logics, Dempster-Shaefer theory and so on. That aside...

Neural networks can be modeled with probability, but that doesn't mean they actually compute in that way. Just like with humans - we can see brain often follows things like Bayes rule, but it doesn't compute PDFs. Doing full probability reasoning would be too expensive for NNs to do, so they cut corners somewhere, and we don't really understand where, it might be very inconsistent. It often works but also often fails.