5. Impression Network:

 

Let us think another simple scenario that the discussed kid saw someone took apple from trees and he also observed that trees are planted on earth… From this scenario the kid will get some new impressions like “trees”, “earth”, “leaves of trees”, “apple flower” etc.

Now the kid has a predefined knowledge base, this knowledge base can only help him to make relation / decision from the impressions he gets by his basic five senses. So whenever he experiences an impression he will put it in an orderly network; a network of impressions. See the following chain

 

trees - PLANTED ON - earth

   |

GROWS ----------- apple leaves

   |                                     

flowers                                

   |                                       

GROWS                             

   |                                        

apple ----------- HAS ----------- apple leaves

 

On the above network small case words are impressions and the capital with bold words are predefined KB values. So impressions making a relational network with predefined knowledge base. So whenever we experienced a new impression, we put the new impression in the existing network or start a new network and finally we are in a continuous process of building a network.

From any branch of the network we can extract information, logic, and decision and generate new knowledge by combining different types of impression. If we can parse the impression network properly by natural language processing, we can get valid statement from the network.

Apple cannot fly

The above statement can be found if the “apple” and “bird” exists on the network.

This concept will be clearer if we categorize the impressions around us, like “swim”, “eat”, “fly”... these are activity type impressions. We can understand any object is flying or swimming only by seeing or only by touching we can identify any moving object.

That means always we do not need all our five basic senses to get any impression, like only using our sight sense and touch sense we can get any activity type impression and explain the impression by relation with other types of impression through predefined KB values. For example, we can explain the impression of “swimming” following way

Swim = move in water by movements of arms and legs or tail

Here underlined words are impressions and bold words are predefined KB values