The Brain as a Universal Learning Machine
This article presents an emerging architectural hypothesis of the brain as a biological implementation of aUniversal Learning Machine. I present a rough but complete architectural view of how the brain works under the universal learning hypothesis. I also contrast this new viewpoint - which comes from computational neuroscience and machine learning - with the older evolved modularity hypothesis popular in evolutionary psychology and the heuristics and biases literature. These two conceptions of the brain lead toverydifferent predictions for the likely route to AGI, the value of neuroscience, t...