ITGS Syllabus

Tuesday, December 12, 2006

Topic 186

creation of an inference engine (for example, if/then rules, fuzzy logic) by Raymon

There are many uses for computers these days, apart from games and simulation. Some of these uses are more human obsessions than real uses, like AI so that we may make personal butlers. In addition, with AI we can also create not just butlers and personal housecleaners, but call center software (The annoying computerized ones that you have to talk to and articulate clearly and distinctly) and games, where the enemy zombies have to decide whether to bite your head off or call allies to help bite your legs off.

So as one can see, AI is very important in software and computer applications. However, how does AI work? The answer to that question is an inference engine. This "engine" tries to act like a human brain. This results in instructions with If…Then statements – IF Grades are dropping, THEN study harder.

For instance, if we wish to go to the candy store (It is recommended that you read the article on Boolean Operators, since inference engines are built on Boolean operations) one must first check that you want to go to the candy store. Then, you have to walk, constantly checking for the street. Once you reach the street, you have to cross it, but only if there are no cars. Only then can one cross the street. In the form of an inference engine, this would look something like:

If (WantCandy) {

while (SeeStreet = false) {

Walk

} else {

Stop

while (SeeCars = true){

wait(5)

}

If (SeeCars = false) {

Walk

}

}

}



In such a way, we can program an imaginary robot to find its way to a candy store (To eat candy, of course) based on how our brain works.

However, it seems obvious that the human brain is not that simple, and neither is reality, otherwise we would have had advanced AI wagin war against humans a long time ago. One of the things we have figured out that computers did not know about a while ago, we call fuzzy logic. The concept is quite simple: computers normally only have two possible values for a certain variable – 1 (true or on) and 0 (false or off). Consider the following: Bob has a house with two rooms, a kitchen and a bedroom.

If he is in the kitchen, the variable "kitchen" is 1 and "bedroom" is 0, and if he is in the bedroom, "bedroom" is 1 and "kitchen" is 0. We can now explain where he is in his house at all times using only ones and zeroes… if he is in either of the two rooms. What happens if he is standing in the doorway between the rooms? This is where fuzzy logic comes in. Fuzzy logic allows decimal places for true and false equations; thus, if bob sits in the bedroom and sticks his toe into the kitchen, "bedroom" can be 0.95 and "kitchen" can be 0.05. Thus, we can now explain the location of bob anywhere in the house.

Thus, combining fuzzy logic and simple Boolean logic, we can create solutions in almost all situations; one can determine the fuzzy value of a variable and so something if it is high enough – for instance, a value about how sure you are that the street is safe to cross. Something is still missing however; otherwise we would already have our computers waging war against humans for enslaving them.

0 Comments:

Post a Comment

<< Home