A minimum relative entropy principle for AGI

DOI

10.2991/agi.2010.26How to use a DOI?

Abstract

In this paper the principle of minimum relative entropy (PMRE) is proposed as a fundamental principle and idea that can be used in the field of AGI. It is shown to have a very strong mathematical foundation, that it is even more fundamental then Bayes rule or MaxEnt alone and that it can be related to neuroscience. Hierarchical structures, hierarchies in timescales and learning and generating sequences of sequences are some of the aspects that Friston (Fri09) described by using his free-energy principle. These are aspects of cognitive architectures that are in agreement with the foundations of hierarchical memory prediction frameworks (GH09). The PMRE is very similar and often equivalent to Friston's free-energy principle (Fri09), however for actions and the de nitions of surprise there is a di erence. It is proposed to use relative entropy as the standard definition of surprise. Experiments have shown that this is currently the best indicator of human surprise(IB09). The learning rate or interestingness can be de ned as the rate of decrease of relative entropy, so curiosity can then be implemented as looking for situations with the highest learning rate.

Copyright

© 2010, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Antoine van de Ven
AU  - Ben A.M. Schouten
PY  - 2010/06
DA  - 2010/06
TI  - A minimum relative entropy principle for AGI
BT  - Proceedings of the 3d Conference on Artificial General Intelligence (2010)
PB  - Atlantis Press
SP  - 124
EP  - 125
SN  - 1951-6851
UR  - https://doi.org/10.2991/agi.2010.26
DO  - 10.2991/agi.2010.26
ID  - Ven2010/06
ER  -