Mozart was a child prodigy. He started playing piano at age 4, and at age 5 he started composing piano pieces that are still played today. He wrote a symphony at age 8 and an opera at 14. There is a legend that as a child, he heard a choir sing an Allegri piece and went home and transcribed the entire thing from memory.

With a neural network, you wouldn’t be able to mathematically prove that the signal is perfectly recovered 100% of the time for all possible inputs. That is the case with PNG and FLAC. If you’re just listening to music and need a good compression ratio, then sure, it won’t be a big deal if a couple of bits are wrong. But that’s also why we have lossy compression. If the goal is to make signal degradation imperceptible to a human, then you could get a much better compression ratio using neural networks. If it’s truly critical that the signal isn’t corrupted, it would probably be better to just use the original method.