Artificial Intelligence and Definition of Intelligence / IDSIA

IDSIA Dalle Molle Institute for Artificial Intelligence Research, Switzerland

http://www.vetta.org/documents/A-Collection-of-Definitions-of-Intelligence.pdf

pdf: by Shane Legg and Marcus Hutter

Introduction

Despite a long history of research and debate, there is still no standard def-

inition of intelligence. This has lead some to believe that intelligence may be

approximately described, but cannot be fully defined. We believe that this de-

gree of pessimism is too strong. Although there is no single standard definition,

if one surveys the many definitions that have been proposed, strong similarities

between many of the definitions quickly become obvious. In many cases differ-

ent definitions, suitably interpreted, actually say the same thing but in different

words. This observation lead us to believe that a single general and encompass-

ing definition for arbitrary systems was possible. Indeed we have constructed

a formal definition of intelligence, called universal intelligence [21], which has

strong connections to the theory of optimal learning agents [19].

Rather than exploring very general formal definitions of intelligence, here we

will instead take the opportunity to present the many informal definitions that

we have collected over the years. Naturally, compiling a complete list would be

impossible as many definitions of intelligence are buried deep inside articles and

books. Nevertheless, the 70 odd definitions presented below are, to the best

of our knowledge, the largest and most well referenced collection there is. We

continue to add to this collect as we discover further definitions, and keep the

most up to date version of the collection available online [22].

(see PDF for the 70 definitions considered in forming their definition.)

Is a single definition possible?

In matters of definition, it is difficult to argue that there is an objective sense in which one definition could be considered to be the correct one. Neverthe-less, some definitions are clearly more concise, precise and general than others.

Furthermore, it is clear that many of the definitions listed above are strongly related to each other and share many common features. If we scan through the definitions pulling out commonly occurring features we find that intelligence is:

• A property that an individual agent has as it interacts with its environment or environments.

• Is related to the agent’s ability to succeed or profit with respect to some goal or objective.

• Depends on how able to agent is to adapt to different objectives and environments.

Putting these key attributes together produces the informal definition of intelligence that we have adopted,

“Intelligence measures an agent’s ability to achieve goals in a wide range of environments.” S. Legg and M. Hutter

Features such as the ability to learn and adapt, or to understand, are implicit in the above definition as these capacities enable an agent to succeed in a wide range of environments. For a more comprehensive explanation, along with a mathematical formalisation of the above definition, see [21] or our forthcoming journal paper.

Comment: The question remains, how can this definition of intelligence be tested in an individual?

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s