Universal Intelligence: A Definition of Machine Intelligence

  title={Universal Intelligence: A Definition of Machine Intelligence},
  author={Shane Legg and Marcus Hutter},
  journal={Minds and Machines},
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 known informal 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… 

An Approximation of the Universal Intelligence Measure

This paper studies the practical issues involved in developing a real-world UIM-based performance metric and develops a prototype implementation which is used to evaluate a number of different artificial agents.

Measuring the intelligence of an idealized mechanical knowing agent

The intelligence level of a mechanical knowing agent is defined to be the supremum of the computable ordinals that have codes the agent knows to be codes of computable Ordinals.

Real-World Limits to Algorithmic Intelligence

It is argued that the world can only be known through the application of rules to observations, and that beyond these rules no knowledge can be obtained about the origin of the authors' observations.

Is Intelligence Artificial?

The idea of intelligence, in the sense of a pro-active or conscious event, is put into a more passive, automatic and mechanical context and the paper suggests looking at intelligence and consciousness as being slightly different.

Chapter 16 Theories of Artificial Intelligence — Meta-theoretical considerations

There cannot be any good theory of intelligence (since intelligence is so complicated, though the authors' work is obviously central to it), because the human brain itself is the best model of intelligence.

A Measure of Real-Time Intelligence

It is shown that there exist agents with intelligence arbitrarily close to the theoretical maximum, and that the intelligence of agents depends on their parallel processing capability.

Universal Meta-Definition of Intelligence

The paper presents the main provisions of the new approach and deduces the initial components of the Universal Formalism of Intelligence, which follows directly from the Universal Axiom and is represented by exclusively the highest Universe’s meta-concepts that can solve the said problem.

An Overview of Approaches Evaluating Intelligence of Artificial Systems

The Algorithmic Intelligence Quotient test, derived from Universal Intelligence definition, is currently the most suitable candidate for a practical intelligence evaluation method of artificial systems, although the test has several known limitations.

What Is Machine Intelligence? A Case Study: Stock Market Forecasting Agents

This chapter is a summary of a talk given during the 19th International Multiconference on Advanced Computer Systems held in Miedzyzdroje, Poland in October 2014, and claims the measurement of performance for each of those tasks given is not sufficient to represent agent’s intelligence.

Using AI to Understand Intelligence: The Search for a Catalog of Intelligence Capabilities

An intelligence vocabulary or catalog is proposed in the quest for the boundaries that shape the current discourse of the experts on intelligence to provide and inform researchers, practitioners, journalists, and policymakers, among many others, with a terminology that can be used when defining intelligence.



A Universal Measure of Intelligence for Artificial Agents

The emphasis on learning, adaptation and flexibility common to many definitions implies that the environment is not fully known to the agent, so intelligence is the ability to deal with a wide range of possibilities, not just a few specific situations.

A Formal Measure of Machine Intelligence

A number of well known informal definitions of human intelli-gence that have been given by experts are taken and formalised to produce a general measure of intelligence for arbitrary machines, which formally captures the concept of ma-chine intelligence in the broadest reasonable sense.

Mathematical definition of"intelligence"(and consequences)

The UACI is an intelligent entity that is simultaneously as intelligent as any other entity (asymptotically) in every dimension simultaneously - this makes intelligence "one dimensional" again and explains why "IQ" is a useful quantity.

Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions

This work unifies both theories of universal induction and gives strong arguments that the resulting universal AIξ model behaves optimally in any computable environment, which is still superior to any other time t and length l bounded agent.

A Native Intelligence Metric for Artificial Systems

Using this definition of native intelligence, a chance elimination argument in the literature is employed to form a simple, but promising native intelligence metric.

The social embedding of intelligence: towards producing a machine that could pass the Turing Test

I claim that to pass the Turing Test over any period of extended time, it will be necessary to embed the entity into society. This chapter discusses why this is, and how it might be brought about. I

The Social Embedding of Intelligence

I claim that to pass the Turing Test over any period of extended time, it will be necessary to embed the entity into society. This chapter discusses why this is, and how it might be brought about. I

A Formal Definition of Intelligence Based on an Intensional Variant of Algorithmic Complexity

The idea that “intelligence is the ability of comprehension” is formed understanding this last term in a formal way: explanatory compression.

Tests of Machine Intelligence

This paper provides a short survey of the many tests of machine intelligence that have been proposed and suggests alternatives to the Turing test and its many derivatives.

Outline for a theory of intelligence

  • J. Albus
  • Psychology
    IEEE Trans. Syst. Man Cybern.
  • 1991
A model is proposed that integrates knowledge from research in both natural and artificial systems and consists of a hierarchical system architecture that performs behavior generation, world modeling, sensory processing, and value judgment.