Analyzing creativity of students with neural networks

Creativity of middle school students was measured with Williams Creativity Test B (WCTB) and Adolescent Scientific Creativity Scale (ASCS). The SOM neural network was used to cluster the data, and three categories were obtained. 70% of the students were used as modeling group, and the other as testing group. Using generalized regression neural network (GRNN) and multivariable linear regression (MLR) to set model and test respectively. Scores of WCTB were used as input and independent variable, ASCS scores used as output and dependent variable. The result showed GRNN was better than MLR.