Intelligent Systems And Their Societies Walter Fritz



Intelligent Systems


Here you will find a definition of "intelligence" and also what exactly a "system" is. You will find the properties and the internal functioning of an "intelligent system" explained in detail.


What is Intelligence
There are many definitions of intelligence. A person that learns fast or one that has a vast amount of experience, could be called "intelligent". However for our purposes the most useful definition is: the systems comparative level of performance in reaching its objectives. This implies having experiences where the system learned which actions best let it reach its objectives.
For details see: What is intelligence? ( Enter for continuous reading, like a book).
By the way, persons are not intelligent in all areas of knowledge, they are only intelligent in those areas where they had experiences. For details see Generality of Intelligence? ( Enter for continuous reading, like a book).


What is a System
A system is part of the universe, with a limited extension in space and time. What is outside the frontier of the system, we call its environment. Stronger or more correlations exist between one part of the system and another, than between this part of the system and parts in the environment.
See System ( Enter for continuous reading, like a book).


What is an Intelligent System
An intelligent system learns how to act so it can reach its objectives.
Here is a Definition of the intelligent system ( Enter for continuous reading, like a book).


Preliminary remarks on the Theory of Intelligent Systems
Here you will see how we developed the concept of the intelligent system and that we were astonished to find out that not only persons but even an artificial intelligent system in a computer needs to forget and sleep.
Have a look at Preliminary remarks on the Theory of Intelligent Systems ( Enter for continuous reading, like a book).


Overview of the Intelligent System
For a diagram and the relationship of the various functions of the intelligent system see:
Overview of the Intelligent system ( Enter for continuous reading, like a book).


Details of the Intelligent System
The main processes occurring within the intelligent systems are the following: The Intelligent System has a temporary objective, that it has derived from its main objective. It senses its environment, although we have to realize that it has only a few senses and that these can only capture, for instance, light and sound of an object, but cannot capture or know the object itself.
The system then stores these sense impressions as elementary concepts. Concepts are a material way of storing information. Working on concepts it creates new ones and stores relationships to other total, part, abstract and concrete concepts. In the following we explain this in more detail.
Of course you realize that there is a difference between an object or occurrence in the environment, the concept the system uses for its internal processing and the word it uses to communicate about the concept.
To continue with the internal processes, in more intelligent systems there should now be a check of the incoming information. With all the information, expressed as concepts, the system builds up the present situation. Now it looks into its memory and finds applicable response rules. It chooses one of the best it has found and performs the corresponding action. Response rules are a field of storage that includes the present situation to which the rule is applicable and the corresponding action.
The intelligent system continually records the present situation and the action that followed as a response rule. The very first response rules are due to chance actions and to teaching.
When the system is externally inactive, that is it sleeps, it reviews the response rules stored in its memory and performs some generalizations. It makes abstractions of concepts and creates the corresponding response rules, including these abstractions. Further comparisons are between the situation and action of a series of recently learned response rules as well as comparisons between situations of different response rules and between actions of different response rules. By all these activities, starting with very concrete response rules, it creates response rules that are applicable to several different but similar situations.
After some while, its memory is full and it forgets the least used concepts and response rules.
In the biological brain, response rules and concepts are a group of neurons. In an artificial intelligent system, both are data structures.
All this is explained at some length in Details of the Intelligent System ( Enter for continuous reading, like a book).


Now you have gained a detailed knowledge of ISs. You have observed the role played by concepts, be they concrete, composite, or abstract and the role played by response rules. You have seen that most observed activity in an IS is based on response rules, chosen for the present subobjective.


If you liked this page, please do me a favor: Tell your friends about it.
The author appreciates comments and suggestions.


For continuous reading, like a book - continue here
Jump to e-book Contents / top of this page

Last Edited 15 Nov. 2014 / Walter Fritz
Copyright © New Horizons Press