University of Cambridge > > Engineering Safe AI > Solomonoff Induction and a Definition of Intelligence

Solomonoff Induction and a Definition of Intelligence

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Adrià Garriga Alonso.

This talk will provide some answers towards the question of “How to choose a prior for your view of the Universe” and from there go on to suggest a universal definition of intelligence.

Firstly, we will cover Solomonoff induction (Solomonoff ’64), and then move on to define an idealised agent AIXI (Hutter ’07) and from that define Hutter-Legg Intelligence (Legg, Hutter ’07).

This talk is part of the Engineering Safe AI series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity