Fisher & KNN & LEM2 AI Package

This Package consist of Fisher AI package, KNN AI package and LEM2 AI package

K neariest neighbours is a self learning application basically used for classification and regression. It can foresee the values of the decision systems (decision system is an array with values, which represents parameters/actions/etc and decisions made for them) which is perfect for AI in games. Thanks to knn you can simulate intelligent behavior of npc or simulate the stock exchange values and many more purposes.

Basically Fisher Method is about selecting most important attributes in loaded decision system. The decision system is an array with numbers, For example each column (except the last one) describes some parameter or action, the last column is a decision given for the actions/parameters described in each line of the array. Some parameters/actions are more important than the others and got higher influence on given decision. This program helps you to select the n numbers of most important parameters/actions of the loaded decision system.

LEM2 is basically an ready application for generating the rules of applied decision system. It allows you to generate rules by "Learn from Examples by Modules", "Exhaustive" and "Sequential Covering" methods.

Asset is great for learning the knn, fisher and lem ideology (school purposes), but it can be easly modified to use in games.