Original article was published on Artificial Intelligence on Medium
Artificial Intelligence problems span a very broad spectrum. They appear to have very little in common except that they are hard.
AI Research of earlier decades results into the fact that intelligence requires knowledge.
Knowledge possess following properties:
- It is voluminous.
- It is not well-organised or well-formatted.
- It is constantly changing.
- It differs from data. And it is organised in a way that corresponds to its usage.
AI technique is a method that exploits knowledge that should be represented in such a way that:
- Knowledge captures generalisation. Situations that share common properties are grouped together. Without the property, inordinate amount of memory and modifications will be required.
- It can be easily modified to correct errors and to reflect changes in the world.
- It can be used in many situations even though it may not be totally accurate or complete.
- It can be used to reduce its own volume by narrowing range of possibilities.
There are three important AI techniques:
- Search — Provides a way of solving problems for which no direct approach is available. It also provides a framework into which any direct techniques that are available can be embedded.
- Use of knowledge — Provides a way of solving complex problems by exploiting the structure of the objects that are involved.
- Abstraction — Provides a way of separating important features and variations from many unimportant ones that would otherwise overwhelm any process.