4. The Concepts behind “Real Intelligence”.

 

When we say human intelligence, here appear two factors for dealing intelligence- these are

1.   Five basic senses

2.   Predefined or natural knowledge or instinct 

Let's see how these two factors are playing in the “real intelligence” system -

4.1. Five basic senses:

When any object exists or any object’s activities happen around us, our five basic senses (1. Sight, 2. Taste, 3. Touch, 4. Sound, 5. Smell) observe that object and the object’s activity. While observing any object or activity our senses set different sense values according to sense type; for example let us consider a new born baby who has no knowledge about this world, and now imagine in front the baby, there is an apple on a plate.

The new born baby! who has no intelligence, he can only see something or hold something around him, and there is an apple on a plate in front of the baby. And obviously the baby does not know anything about “Apple”.

Let’s observe the baby’s activities:

1.   The baby crawling to the apple,

2.   See the apple

3.   Hold the apple

4.   Take up the apple from the plate

5.   Smell the apple

6.   Bite the apple

7.   Get a sweet taste of the apple

 

Now the five basic senses assign some values for the “Apple” (for simplicity we are only considering the very basic observations and avoiding the plate, later we will consider the relation between the apple and the plate) in following ways

 

Sight => color=radish; shape=round

Taste => sweet

Touch => hard

Sound => no sound

Smell => sweet

Now the baby acquires some knowledge about that apple and in future when he will see another object with similar sense properties, he will treat that as apple. And reversely we also find another scenario that - after assigning the sense values the baby himself automatically take a name which can help him to uniquely identify apple from other objects. As the boy is very little and has no knowledge about the world and even he cannot pronounce perfectly so we found that after recognizing an apple, he is calling it as “apalam”. Now if someone say “apalam”, the baby get an impression of a round, radish and sweet taste object.

After time passed when the baby grows up and now can pronounce correctly and when he becomes hungry, he can feel it, someone learns him that “it is called apple which you were addressing as “apalam” and it is a fruit, when you get hungry you can eat it”. The kid has learned now the object apple with the same sense values.

Now let’s consider the kid found another object with the following sense properties

Sight => color=orange; shape=round
Taste => sweet
Touch => hard
Sound => no sound
Smell => sweet

He found that the 2nd object has almost same sense properties as 1st object except the “color”. So he can easily come to a decision that it is also a fruit when he becomes hungry he can eat it. And later he comes to know that the 2nd object was an orange.

(Here for simplicity complex & detail sense properties have been avoided, only for pointing that an intelligent system can be developed using our basic sense values.)

Now read the word “Apple”. After reading this word, did you notice that an impression raises in your mind like that “A radish color round sweet fruit”. Right? Now if I tell you “Orange” another impression will be recalled like “A orange color round sweet fruit”. These impressions are actually a set of sense properties, those were made by you when you see any objects, then you make group according to sense values. For example; you have already made a group named “Fruit” because you got the similarities in the sense values of the group members.

And also if you observed any rule for any object of the group, you will set the same rule for all members of the group. For example if I say that “Apple juice can be a good base flavor for water”. You will also learn a new rule that “Orange juice also can be a good base flavor for water” because you put the apple and orange in the same group.

In this way you are developing your knowledge base by using existing knowledge and without any target like other AI algorithms.

Now again let's come to the kid who can recognize fruits only. When he hears about an unknown object; he will want to know the sense properties of that unknown object. In this case he will do query like following, for example if say him “Car”, he will want to know

What is the color of car?

Does it taste sweet?

How it will feel after touching?

Has it a good smell?

Above queries are related to sense properties of a fruit. Because the kid’s knowledgebase has developed from recognizing fruits. When the kid will observe another type of object with his five basic senses, like “car” and also activities of the object, there will add a new impression in the knowledge. And accordingly similar objects will create different groups according to their sense properties and activities. 

4.2. Predefined or natural knowledge or instinct.

Let's go back to previous section, a newborn baby’s experience after seeing an apple. Let’s review the activities again - a newborn baby sees an apple and following events have occurred-

-The baby crawling to the apple,
-See the apple
-Hold the apple
-Take up the apple from the plate
-Smell the apple
-Bite the apple
-Get a sweet taste of the apple

 

Let’s consider that the apple and the plate have placed at right side of the baby. So after seeing the apple the baby wants to move to right side of him. After reaching at the apple he has to hold and put the apple from plate and take it to mouth to taste it. When he gets a good smell and sweet flavor, he will decide to eat the apple. But if the baby got any object with bad smell and flavor, he will reject it.

Did you notice that, here some activities performed by the baby those were not trained him. For example the apple and plate was at the right side of the baby, so he moved to right, but no one learnt him such lesson like that “if any object situated to right side then you have to move yourself to right side”, same way he put up the apple from plate to bite it, here no need to learn the baby that “you have to hold the apple to put it up”. After putting up the apple from the plate the baby will automatically discover the relation between the apple and the plate, that is “on”, that means “apple on the plate”

Here we found that the baby already has the knowledge of directions (right, left, up, down), for that he knows that he has to move right if anything need to hold that is on right side. He can take some decisions without learning anything, like if he got any bad smell or flavor from something, he will not eat it. He can understand relation between objects like an apple on the plate or plate on the table. Predefined knowledge base is playing the role to understand these kinds of relations or taking decisions just based on senses value (Like bad smell objects cannot be eaten or moving right to get something on right side). Some other example of predefined knowledge base are like counting knowledge - If anyone does not have the knowledge of number system, though the can count, suppose there were two apples on the plate and one apple has taken by someone in front of the baby, though the baby does not have the number sense, he will understand one apple is missing between two.

Now we will see how the soul algorithm use the above concepts to learning anything, taking decision, acquiring new knowledge using existing knowledge, feeling something (sorrow or joy, justice or injustice), and finally we will explain why it is named soul algorithm, and also why it is not only a real intelligent algorithm, but also it contains a soul like living being. That's why it can learn itself; no need to set it a target to learn about that.