Machines Like Us – Science News

Researchers Shane Legg and Marcus Hutter have updated their paper defining machine intelligence, originally posted in June of this year. After six months of study, they have extracted the essential features common to all these definitions and created a mathematically formal definition of machine intelligence that can be applied to arbitrary machines. From the paper's abstract:

A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: We take a number of well knowninformal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.

Read complete paper here (PDF).