Yann LeCun gave this cake analogy in NIPS 2016:
If we think of our brain as a cake, then the cake base is unsupervised learning. The machine predicts any part of its input for any observed part (e.g. future frames in videos), all without the use of labelled data. Supervised learning forms the icing on the cake, and reinforcement learning is the cherry on top.
In NIPS 2017, Pieter Abbeel reused this cake analogy to describe his paper §andrychowicz2017_hindsight_experience_replay: “Intelligence is a cake with many cherries”