General Intelligence

After reviewing extensive literature on the subject, Legg and Hutter^[11]] summarizes the many possible valuable definitions in the informal statement “Intelligence measures an agent’s ability to achieve goals in a wide range of environments.” They then show this definition can be mathematically formalized given reasonable mathematical definitions of its terms. They use Solomonoff induction - a formalization of Occam's razor - to construct an universal artificial intelligence with a embedded utility function which assigns less utility to those actions based on theories with higher complexity. They argue this final formalization is a valid, meaningful, informative, general, unbiased, fundamental, objective, universal and practical definition of intelligence.

We can relate Legg and Hutter's definition with the concept of optimization. According to Eliezer Yudkowsky intelligence is efficient cross-domain optimization [2]. It measures an agent's capacity for efficient cross-domain optimization of the world according to the agent’s preferences preferences.^[32]]. Optimization measures not only the capacity to achieve the desired goal but also is inversely proportional to the amount of resources used. It’s the ability to steer the future so it hits that small target of desired outcomes in the large space of all possible outcomes, using fewer resources as possible. For example, when Deep Blue defeated Kasparov, it was able to hit that small possible outcome where it made the right order of moves given Kasparov’s moves from the very large set of all possible moves. In that domain, it was more optimal than Kasparov. However, Kasparov would have defeated Deep Blue in almost any other relevant domain, and hence, he is considered more intelligent.

1. ^{^}

   http://arxiv.org/pdf/0712.3329.pdf

2. ^{^}

   http://intelligence.org/files/IE-EI.pdf

• Optimization process
• Decision theory
• Rationality
• Intelligence as efficient cross-domain optimization
• Legg and Hutter paper “Universal Intelligence: A Definition of Machine Intelligence”

General Intelligence or Universal Intelligence is the ability to efficiently achieve goals in a wide range of domains. 

But the word “intelligence”“intelligence” commonly evokes pictures of the starving professor with an IQ of 160 and the billionaire CEO with an IQ of merely 120. Indeed there are differences of individual ability apart from “book smarts”“book smarts” which contribute to relative success in the human world: enthusiasm, social skills, education, musical talent, rationality. Note that each factor I listed is cognitive. Social skills reside in the brain, not the liver. And jokes aside, you will not find many CEOs, nor yet professors of academia, who are chimpanzees. You will not find many acclaimed rationalists, nor artists, nor poets, nor leaders, nor engineers, nor skilled networkers, nor martial artists, nor musical composers who are mice. Intelligence is the foundation of human power, the strength that fuels our other arts.

Definitions of General Intelligence

After reviewing extensive literature on the subject, Legg and Hutter [1] summarizes the many possible valuable definitions in the informal statement “Intelligence measures an agent’s ability to achieve goals in a wide range of environments.” They then show this definition can be mathematically formalized given reasonable mathematical definitions of its terms. They use Solomonoff induction - a formalization of Occam's razor - to construct an universal artificial intelligence with a embedded utility function which assigns less utility to those actions based on theories with higher complexity. They argue this final formalization is a valid, meaningful, informative, general, unbiased, fundamental, objective, universal and practical definition of intelligence.

We can relate Legg and Hutter's definition with the concept of optimization. According to Eliezer Yudkowsky intelligence is efficient cross-domain optimization [2]. It measures an agent's capacity for efficient cross-domain optimization of the world according to the agent’s preferences [3]. Optimization measures not only the capacity to achieve the desired goal but also is inversely proportional to the amount of resources used. It’s the ability to steer the future so it hits that small target of desired outcomes in the large space of all possible outcomes, using fewer resources as possible. For example, when Deep Blue defeated Kasparov, it was able to hit that small possible outcome where it made the right order of moves given Kasparov’s moves from the very large set of all possible moves. In that domain, it was more optimal than Kasparov. However, Kasparov would have defeated Deep Blue in almost any other relevant domain, and hence, he is considered more intelligent.

One could cast this definition in a possible world vocabulary, intelligence is:

1. the ability to precisely realize one of the members of a small set of possible future worlds that have a higher preference over the vast set of all other possible worlds

IntelligenceGeneral in general or Universal Intelligence is the ability to efficiently achieve goals in a wide range of domains.

This tag is specifically for discussing intelligence in general or human intelligence in the broad sense.

Forsense: for discussion of IQ testing and psychometric intelligence, see IQ / g-factor; for discussion about e.g. specific results in artificial intelligence, see AI. These are distinct tags but may overlap with this tagone to the extent that they discuss the nature of general intelligence.

Intelligence in general or Universal Intelligence is the ability to efficiently achieve goals in a wide range of domains. After reviewing extensive literature on the subject, Legg and Hutter 1 summarizes the many possible valuable definitionsThis tag is specifically for discussing intelligence in general or human intelligence in the informal statement “Intelligence measures an agent’s abilitybroad sense.

For discussion of IQ testing and psychometric intelligence, see IQ / g-factor; for discussion about e.g. specific results in artificial intelligence, see AI. These are distinct tags but may overlap with this tag to achieve goalsthe extent that they discuss the nature of general intelligence.

Examples of posts that fall under this tag include The Power of Intelligence, Measuring Optimization Power, Adaption-Executers not Fitness Maximizers, Distinctions in Types of Thought, The Octopus, the Dolphin and Us: a wide range of environments.” They then show this definition can be mathematically formalized given reasonable mathematical definitions of its terms. They use Solomonoff induction - a formalization of Occam's razor - to construct an universal artificial intelligence with a embedded utility function which assigns less utility to those actions based on theories with higher complexityGreat Filter tale. They argue this final formalization is a valid, meaningful, informative, general, unbiased, fundamental, objective, universal

On the difference between psychometric intelligence (IQ) and practical definition of intelligence.general intelligence:

We can relate Legg and Hutter's definition with

But the concept of optimization. According to Eliezer Yudkowskyword “intelligence is efficient cross-domain optimization 2. It measures an agent's capacity for efficient cross-domain optimization” commonly evokes pictures of the world accordingstarving professor with an IQ of 160 and the billionaire CEO with an IQ of merely 120. Indeed there are differences of individual ability apart from “book smarts” which contribute to the agent’s preferences 3. Optimization measures not only the capacity to achieve the desired goal but also is inversely proportional to the amount of resources used. It’s the ability to steer the future so it hits that small target of desired outcomesrelative success in the large spacehuman world: enthusiasm, social skills, education, musical talent, rationality. Note that each factor I listed is cognitive. Social skills reside in the brain, not the liver. And jokes aside, you will not find many CEOs, nor yet professors of all possible outcomes, using fewer resources as possible. For example, when Deep Blue defeated Kasparov, it was able to hit that small possible outcome where it made the right order of moves given Kasparov’s moves from the very large set of all possible moves. In that domain, it was more optimal than Kasparov. However, Kasparov would have defeated Deep Blue in almost any other relevant domain, and hence, he is considered more intelligent.

One could cast this definition in a possible world vocabulary,

We can relate Legg and Hutter's definition with the concept of optimization. According to Eliezer Yudkowsky intelligence is efficient cross-domain optimization 2. It measures an agent's capacity for efficient cross-domain optimization of the world according to the agent’s preferences 3. Optimization measures not only the capacity to achieve the desired goal but also is inversely proportional to the amount of resources used. It’s the ability to steer the future so it hits that small target of desired outcomes in the large space of all possible outcomes, using fewer resources as possible. For example, when Deep Blue defeated Kasparov, it was able to hit that small possible outcome where it made the right order of moves given Kasparov’s moves from the very large set of all possible moves. In that domain, it was more optimal than Kasparov. However, Kasparov would have defeated Deep Blue in almost any other relevant domain, and hence, ithe is considered more intelligent.

Intelligence in general or Universal Intelligence is the ability to efficiently achieve goals in a wide range of domains. After reviewing extensive literature on the subject, Legg and Hutter 1 summarizes the many possible valuable definitions in the informal statement “Intelligence measures an agent’s ability to achieve goals in a wide range of environments.” They then show this definition can be mathematically formalized given reasonable mathematical definitions of its terms. They use Solomonoff induction] - a formalization of Occam's razor - to construct an universal artificial intelligence with a embedded utility function which assigns less utility to those actions based on theories with higher complexity. They argue this final formalization is a valid, meaningful, informative, general, unbiased, fundamental, objective, universal and practical definition of intelligence.