Rethinking fair supervised learning by treating it as reinforcement learning with a corrupted reward channel, and introducing a new criterion for corrupt reward reinforcement learning as a result.
- We can recast supervised learning tasks as reinforcement learning tasks with a corrupted reward signal
Over the course of a few months in late 2017 and early 2018, I gave several talks around Cleveland introducing audiences to deep learning. This post describes my experiences along the way.
These talks were slight variations on a core thesis – that deep learning is essentially a collection of methods for learning hierarchical, distributed representations. This may not seem all that controversial, but I find that the usual methods of introducing deep learning, e.g. “neuroscience-inspired machine