The concept that computers can be programmed to assume capabilities

such as learning, reasoning, adaptation and self correction.

A sub field of ai addresses creativity both theorotically and practically. A related area of

computational research is artificial intution and artificial imagination.

The general problem of simulating intelligence have been broken down into a number of specific sub-problems. These consist of

particular traits or capabilities that researchers would like an intelligent system to display but they are not always able to display

the accurate information.

In the 1940s and 1950s, a number of researchers explored the connection between neurology, information theory,

and cybernetics. Some of them built machines that used electronic networks to exhibit rudimentary intelligence, such

as W. Grey Walter's turtles and the Johns Hopkins Beast

Over the past couple decades much work, and progress, has been made in the pursuit of creating artificial minds and

lifelike humanoid movement. Researchers from many different nations have experimented with recreating realistic

human characteristics - with some success. Honda's humanoid robot ASIMO leads the way in mobility

Machine learning has been central to AI research from the beginning. Unsupervised learning

is the ability to find patterns in a stream of input. Supervised

learning includes both classification and numerical regression. Classification is used to determine what

category something belongs in, after seeing a number of examples of things from several categories.

 AI researchers developed sophisticated mathematical tools to solve specific subproblems. These tools are truly scientific, in the sense that their results are both

measurable and verifiable, and they have been responsible for many of AI's recent successes