New research keeps finding things that keep reintroducing symbolic ai structures to machine learning and I have wondered why more research hasnt been done with it. There was a heyday in the 70s for it but after neural nets came out it seems to be completely out of the discussions. I think it could make a comeback if we can resolve the primary issues of self-instantiation and feedback loops. Even using several random reservoir nets and a little bit of math creates strong signals for the component parts that contribute to what something is made of and how it works.