Optimising the parameters of a RBFN network for a teaching learning paradigm

Abstract

Academic performance of students has been a concern worldwide. Despite efforts made by educational institutions there has been a rise in poor academic performance. In our research study we have proposed a model to pre-determine the academic performance of students using a Radial Basis Function network (RBFN) using primary data. The proposed model has been developed by using algorithms like differential evolution (DE) and teaching learning based optimization (TLBO). This model can be used by academic institutions to identify the academically weaker students and take preventive steps to reduce the number of academic failures.