Capturing the implicit relationship between the input and output patterns such that when test input pattern is given, the pattern corresponding to the output of the generalized system is retrieved, is called the problem of pattern mapping. Since the very objective of pattern mapping problem is to capture the implied function and mimic its behavior and therefore it is also termed as function approximation problem. Alternatively, function approximation is the task of learning or constructing a function that generates approximately the same outputs from input vectors as the process being modeled, based on available training data. The approximate mapping system should give an output which is fairly close to the values of the real function for inputs close to the current input used during learning.