[Next] [Up] [Previous]

An (Overly) Simple Design for an Intelligent
System

Here is a simple set of components for an intelligent system.

Perceptual mechanisms

These mechanisms analyze and interpret information taken in by the ``senses'' and store the interpretations in a database.

A database of information

This is not just as a store of facts, for a database can also store information about how to do things. It may include both particular facts provided by the senses and generalizations formed over a period of time.

Analysis and interpretation procedures

These are procedures which examine the data provided by the senses, break them up into meaningful chunks, build descriptions, match the descriptions, etc. Analysis involves describing what is presented in the data. Interpretation involves describing something else, possibly lying behind the data, for instance, constructing a 3-D description on the basis of 2-D images, or inferring someone's intentions from his actions.

Reasoning procedures

These use information in the database to derive further information which can also be stored in the database. If you know that Socrates is a man, and that all men are mortal, you can infer something new, namely, that Socrates is mortal.

A database of goals

These just represent possible situations which it is intended should be made actual. There may also be policies, preferences, ideals, and the like.

Planning procedures

These take a goal, and a database of information, and construct a plan which will achieve the goal, assuming the correctness of the information in the database.

Executive mechanisms and muscles or motors

These translate plans into action.

Often the divisions will not be very clear. For instance, is `this situation is painful' a fact or a goal concerned with the need to change the situation? This sort of system can be roughly represented by figure 1.

[IMAGE ]