On Quantified Analysis and Evaluation for Development Reading Brain Performance Using Neural Networks’ Modeling

Abstract

Recently, neuroscientists, and educationalists as well have revealed some resulted educational interesting findings. Originally those findings have been derived in accordance with commonly increasing sophisticated role of Artificial Neural Networks (ANNs) modeling. Herein, performance evaluation of an observed educational field phenomenon considered via realistic ANN modeling. Briefly, realistic ANNs modeling for analysis, and evaluation of an interdisciplinary challenging phenomenon, has been adopted in this article. More specifically, that realistically modeled phenomenon based originally upon the observable children's reading brain performance in classrooms (equivalently: children's academic achievement). By more details, the adopted educational phenomenon essentially concerned with quantification of the reading children's brain performance that affected by educational physical environment as well as teaching reading methodologies. Furthermore, realistic (ANNs) simulation has been suggested in accordance with the highly specialized neurons' number while performing reading brain function's role. Consequently, realistic simulation for quantifying reading brain function is suggested by adopting (ANNs) modeling. Optimal selectivity for gain factor value, learning rate parameter value, and number of neurons are considered to improve learning reading brain function. Obviously, that function is dynamically involved by enhanced cognitive goal for reading brain process that based on dynamic synaptic interconnectivity. In this context, the presented work illustrates via ANN simulation results: How ensembles of highly specialized neurons could be dynamically involved to perform developing of reading brain's cognitive function. That function considers essentially translation of orthographic word-from into a spoken word (phonological word-form). Interestingly, the realistic ANN model presented herein has been in close resemblance functionally and structurally to biological neuronal systems.