The expression intelligent system is sometimes used for incomplete intelligent systems, for instance for an intelligent house or an expert system. Here we talk about complete intelligent systems. Such a system has senses to gather information from its environment. It can act and has a memory of the results of its actions. It has an objective and by inspecting its memory it can learn from experience, how to better reach its objectives.

For a complete intelligent system all these capabilities have to be present.

Intelligence

Many definitions of “intelligence” are used. For practical purposes we use the following: Intelligence is the systems level of performance in reaching its objectives.

System

A system is part of the universe, with a limited extension in space and time. Stronger or more correlations exist between one part of the system and another, than between this part of the system and parts outside of the system.

Examples of intelligent systems

Human beings and animals are intelligent systems. At present, reseach is advancing in building primitive artificial intelligent systems. Intelligent systems are usually characterized by their ability to adapt to dynamic situations in uncertain environments. This is a high bar that at present only living systems can match. For example, a refrigerator is not an intelligent system since it cannot learn.

Objective

An objective is a certain situation that some systems try to reach. Normally there are many levels of objectives, there can be a main objective and subobjectives. Senses A sense is that part of the system that can receive communications from the environment. Senses are needed so that the intellignt system can know its environment and act accordingly.

Situation

The situation is a series of concepts that the intelligent system uses to express the information estracted from the environment through its senses.

Action rules

An action rule is the result of an experience or the result of observing its memory. It is the physical storage by the intellignt system of a situation and a good corresponding action.

Memory

The memory is the physical storage of concepts and action rules. This includes the situations that the intelligent system has experienced.

Learning

Learning is probably the most important capacity of an intelligent system. It learns concepts from concurrent sense information. It learns action rules from its experience. Acting, possibly haphazard acting, in a certain situation, is stored with a value. An action rule has a higher value if it helped to reach an objective. Learning includes creating abstract concepts based on concrete examples. It includes learning composite concepts containing the pars of of an object. Learnig is also the detection or relationships (patterns) between the situation part of an action rule and the resulting future situation.

See also

• System
• Intelligence
• Machine Learning
• Autonomous System
• Expert system
• Neural net
• Intelligent agent
• Humanoid robots
• Hybrid intelligent system

System (from the Latin (systēma), and this from the Greek (sustēma)) is an assemblage of entity/objects, real or abstract, comprising a whole with each and every component/element interacting or related to another one. ... Intelligence is a property of mind that encompasses many related mental abilities, such as the capacities to reason, plan, solve problems, think abstractly, comprehend ideas and language, and learn. ... As a broad subfield of artificial intelligence, Machine learning is concerned with the development of algorithms and techniques that allow computers to learn. At a general level, there are two types of learning: inductive, and deductive. ... Autonomous system can mean different things: On the Internet, an autonomous system is a collection of IP networks under the control of a single entity; see autonomous system (Internet). ... An expert system also known as a knowledge based system, is a computer program that contains some of the subject-specific knowledge of one or more human experts. ... A neural network is an interconnected group of neurons. ... Simple reflex agent Learning agent In computer science, an intelligent agent (IA) is a software agent that exhibits some form of artificial intelligence. ... A humanoid robot is a robot with its overall appearance based on that of the human body. ... Intelligent systems redirects here. ...

External links

• IEEE Intelligent Systems
• International Journal of Intelligent systems
• IEEE IS 2006
• Intelligent Systems Program
• Intelligent Systems and Robotic Center
• IRIS::Institute of Robotics and Intelligent Systems
• Intelligent Systems and their Societies
• Android World
• NASA's Intelligent Systems Division at Ames Research Center