Representation of Incompletely Specified Index Generation Functions Using Minimal Number of Compound Variables

This paper shows a method to reduce the number of input variables to represent incompletely specified index generation functions. A compound variable is generated by EXORing the original input variables. By using both original and compound variables, incompletely specified index generation functions can be represented by fewer variables. As a means to select variables, a heuristic method using information gains is presented. We compare representing random functions using 1. only original variables, and 2. both original and compound variables. Experimental results show that the use of compound variables effectively reduces the number of input variables.