AI Abstract Series E10: Zeta Distribution and Transfer Learning Problem.

Welcome to the Technocracy A.I. Abstract Series for Published Scientific Work in the A.I. and Artificial General Intelligence field.

Todays paper is titled: Zeta Distribution and Transfer Learning Problem.

Authored By Eray Özkural.

Abstract: We explore the relations between the zeta distribution and algorithmic information theory via a new model of the transfer learning problem. The program distribution is approximated by a zeta distribution with parameter near 1. We model the training sequence as a stochastic process. We analyze the upper temporal bound for learning a training sequence and its entropy rates, assuming an oracle for the transfer learning problem. We argue from empirical evidence that power-law models are suitable for natural processes. Four sequence models are proposed. Random typing model is like no-free lunch where transfer learning does not work. Zeta process independently samples programs from the zeta distribution. A model of common sub-programs inspired by genetics uses a database of sub-programs. An evolutionary zeta process samples mutations from Zeta distribution. The analysis of stochastic processes inspired by evolution suggest that AI may be feasible in nature, countering no-free lunch sort of arguments.

As always thank you for listening to the Technocracy Abstract Series and a special thank you for our sponsors the Foundation, and the AGI Laboratory.


Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.