AI winter and other seasons

When I was at university, many years ago, I took a course on neural networks as part of a Masters degree in artificial intelligence. The lecturer delivering it was really passionate about it, showing us live demos of self-organising maps adapting their topology in response to a given input, and discussing the biomedical studies that had inspired some of the networks that we were studying. He was also clearly frustrated about the lack of interest and credit those methods were getting. He would show examples of neural networks solving tough problems, just to conclude that it was not being applied because "we cannot prove that it works" or "it is too hard to explain". Thinking about it now, when neural network-based AI is everywhere and praised for all the miracles in the world, feels surreal.