Abstract:
Herein, Artificial Neural Network (ANN) Modeling is considered to mathematically
formulate an interesting and rather challenging educational issue; namely, searching for
optimality in an educational methodology for teaching children how to read. The
adopted search approach is inspired by relevant artificial neural network modeling based
on neuro-biological characterizations. That is rather than other classical approaches
inspired by psychological and psycho-linguistics research directions.
Fortunately, dominant optimality of teaching reading phonically over other
methodologies has been recently proven by a simulated but realistic model along with
published results, subsequent to an educational field testing. Consequently,
mathematical formulation of phonics methodology is a highly recommended research
work to justify that optimality. Herein, mathematical formulation performed via
comparative analogy with a naturally inspired artificial neural network (ANN) model.
More precisely, that fulfilled on the basis of realistically simulated modeling of selforganized
(unsupervised) learning paradigm originated from Hebb's learning rule. In
other words, modeling of Hebbian rule essentially depends upon biological information
processing to construct associative memory phenomenon after Pavlovian conditioning
learning. Conclusively, presented mathematical formulation supported superiority as
well as optimality of teaching reading using phonics methodology.