• Corpus ID: 16167158

A Collection of Definitions of Intelligence

@inproceedings{Legg2006ACO,
  title={A Collection of Definitions of Intelligence},
  author={Shane Legg and Marcus Hutter},
  booktitle={AGI},
  year={2006}
}
This chapter is a survey of a large number of informal definitions of “intelligence” that the authors 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 here are, to the authors' knowledge, the largest and most well referenced collection there is. 

Tests of Machine Intelligence

TLDR
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.

Intelligence : Many definitions

TLDR
The 55 definitions presented below are, to the best of their knowledge, the largest and most well referenced collection there is and continue to add to this collect as the authors discover further definitions, and keep the most up to date version of the collection available online.

A machine learning approach for abstraction and reasoning problems without large amounts of data

TLDR
benchmarking is one of the most valuable approaches for the evaluation of artificial intelligence because it is reproducible, scalable, easy to set up, and flexible enough to be applied to a wide variety of possible tasks.

Toward a Formal Characterization of Pragmatic General Intelligence – ROUGH PRELIMINARY VERSION

TLDR
Perhaps the most carefully-wrought formalization of intelligence so far is the theory of ”universal intelligence” presented by Shane Legg and Marcus Hutter in [7], which draws on ideas from algorithmic information theory.

Universal Intelligence: A Definition of Machine Intelligence

TLDR
A number of well known informal definitions of human intelligence are taken, and mathematically formalised to produce a general measure of intelligence for arbitrary machines that formally captures the concept of machine intelligence in the broadest reasonable sense.

(Computational) Intelligence: What's in a Name?

  • J. Bezdek
  • Computer Science
    IEEE Systems, Man, and Cybernetics Magazine
  • 2016
This article is about the terms intelligence, artificial intelligence (AI), and computational intelligence (CI). Topics addressed here include 1) the historical evolution of the terms AI and CI; 2)

Building intelligence, development of an ontological basis and a comparative analysis to characterize the concept

TLDR
This work aims to develop a qualitative inductive analysis between the different characterizations of the term "intelligence" in the areas of computer science and the term associated with architecture and technology of the buildings.

Defining Modes of Intelligence

TLDR
This chapter concerns itself first with trying to define the parameters of intelligence as humans have worked them out, from various points of view, and with how these insights can be applied to non-human intelligence.

Towards General Evaluation of Intelligent Systems: Using Semantic Analysis to Improve Environments in the AIQ Test

TLDR
The analysis identified several classes of programs that are non-discriminative or contain pointless code adversely affecting the testing process, increasing the suitability of the Algorithmic Intelligence Quotient test as a general artificial intelligence evaluation method.

Intelligence, a New Concept?

Humans, or at least the humans reading this book, pride themselves on their intelligence. Humans have by far the most advanced material culture and sophisticated, flexible communication system of any
...

References

SHOWING 1-10 OF 42 REFERENCES

A Native Intelligence Metric for Artificial Systems

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

On the thresholds of knowledge

  • D. LenatE. Feigenbaum
  • Computer Science
    Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications
  • 1988
TLDR
Three major findings in the domain of artificial intelligence are articulated and it is concluded that together these concepts can determine a direction for future AI research.

The Nature of Intelligence

Evaluating Intelligence Hand-wringing, browbeating , and finger-pointing have all followed the events of September 11, 2001, and the National Intelligence Estimate on Iraq's Continuing Programs for

Evaluating intelligence: a computational semiotics perspective

  • R. Gudwin
  • Computer Science
    Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0
  • 2000
TLDR
Methods for evaluating the intelligence of intelligent systems by means of computational semiotics focus on architectural details of structures, organizations, processes and algorithms used in the construction of the intelligent system, evaluating the impact of using these elements in the overall intelligent behavior exhibited by the system.

The Turing Ratio: Metrics For Open-ended Tasks

TLDR
It is argued that evolutionary computation is a key method for amplifying human intelligence, an assertion which future scientists can empirically decide through measuring Turing Ratios and considering task breadth, prior knowledge, and time series of the measures.

Where's the AI?

TLDR
A program exhibiting AI as one that can change as a result of interactions with the user is described, which would have to process hundreds or thousands of examples as opposed to a handful.

WHAT IS ARTIFICIAL INTELLIGENCE

This article for the layman answers basic questions about artificial intelligence. The opinions expressed here are not all consensus opinion among researchers in AI.

AI as Complex Information Processing

TLDR
In this article, a software architecture for intelligent agents is presented, which makes use of the fact that an agent is in a situation, so it only processes some of the information – the part that is relevant to that situation.

Computer science as empirical inquiry: symbols and search

TLDR
Computer science is the study of the phenomena surrounding computers; the machine—not just the hardware, but the programmed, living machine—is the organism the authors study.