The third installation of the ultimate intelligence series was submitted to AGI-2017. Unfortunately, it was not received very well by the reviewers whom found fault with my paraphrasing of the conclusions of Karl Friston’s free energy principle research program. Here is the abstract and the paper for your perusal, what is your opinion?
Abstract. We propose that operator induction serves as an adequate model of perception. We explain how to reduce universal agent models to operator induction. We propose a universal measure of operator induction fitness, and show how it can be used in a reinforcement learning model and a homeostasis (self-preserving) agent based on the free energy principle. We show that the action of the homeostasis agent can be explained by the operator induction model.
My opinion is that it’s exciting to see another item in this series by you. 🙂
Thank you Michael. I am trying to make it into a theoretical book on AGI, many other chapters are planned. I hope machine learning researchers and students will enjoy it, I’m going to put a lot of effort to make it a bit more ambitious than usual.