Abstract:

This research work addresses quantified Investigation of an interesting and challenging issue namely learning creativity phenomenon. It introduces an interdisciplinary novel approach associated with educational sciences: computer simulation of brain functions and practical field (case study) results. Realistic simulation for quantifying, learning creativity is suggested by adopting Artificial Neural Networks (ANNs) modeling. Optimal selectivity for values of gain factor, learning rate parameters , and/or number of neurons are relevant for improvement of quantified learning creativity phenomenon. This phenomenon considered as an interdisciplinary issue associated with educational field applications and activities. Accordingly, for long time ago and till recently, educationalists as well as psychologists have been cooperatively interesting in systematic searching for quantifying , evaluation and improvement of that issue. Accordingly , interdisciplinary research work integrating : cognitive and learning sciences with educational psychology and neurobiology is adopted for quantifying learning creativity phenomenon. This piece of research introduces an interdisciplinary novel approach concerned with evaluation of that interesting issue. Herein, realistically, quantified learning creativity is simulated using (ANNs) modeling. More specifically , presented modeling considers statistically time dependant improvement of learners' achievements (learning convergence time).

Realistic simulation of quantifying learning creativity is suggested by adopting Artificial Neural Networks (ANNs) modeling considering error correction(supervised) paradigm. Moreover , this piece of research considers statistically the time dependant improvement of learners' achievements (learning convergence time). Mainly two design parameters of ANNs proposed for measuring such time improvement of learning creativity. Both parameter are: gain factor (of neuronal sigmoid activation function), and learning rate value. They have effective impact on learning creativity via dynamical synaptic connectivity (brain Plasticity). By either increasing of neurons' number contributing in learning processes or ANNs design parameters . Conclusively, optimal selectivity for values of gain factor , learning rate parameters , and/or number of neurons are relevant for improvement of quantified learning creativity phenomenon.

Herein, the introduced research mainly concerned with learning creativity evaluation using realistic neural system models. Specifically, it considers learners' response time during interactive CAL processes. That is measured as average learning convergence time after obtaining results from a case study and running of a computer simulation programs. Interestingly, some conclusive remarks are presented after analysis of obtained results. These introduced realistic simulation results seemed more valuable and very promising for future elaborate and systematic research in learning creativity phenomenon.

Keywords:

Artificial neural network, Brain functional modeling, Computer aided learning, learning creativity phenomenon.