On assessment of students' academic achievement considering categorized individual differences at engineering education (Neural Networks Approach)

Abstract

This work introduces analysis and evaluation of an interesting, challenging, and interdisciplinary, pedagogical issue. That's originated from categorization of the achievement diversity of students' (individual differences), equivalently students' Structure of the Observed Learning Outcome (SOLO). This students' academic diversity affected in classrooms by three interactive learning/teaching approaches (orientations) namely: surface, deep, and strategic. Assessment of these approaches has been performed via realistic simulation adopting Artificial Neural Networks (ANNs) modeling considering Hebbian rule for coincidence detection learning. That modeling results in interesting mathematical analogy of two effective learning performance factors with students' achievement individual differences. Firstly, the effect of two brain functional phenomena; namely long term Potentiation (LTP) and depression (LTD). That's in accordance with opening time for crossing N-methyl-D-aspartate NMDA observed at hippocampus brain area. Secondly, the effect of neurons' number associated with diverse learning/teaching environments comprise the dichotomy (extroversion/introversion). This dichotomy has been investigated as the external and internal environmental learning conditions. The obtained simulation results concerned with student's diversity attitudes (extroversion/introversion). They shown to be in well agreement with recently published results after performing a case study at an engineering institution in Egypt. Finally, introduced study, aims mainly to present interesting analysis of brain's functional development based students' individual differences, and learning abilities.