In this paper, creativity measurement data was analyzed by neural networks. Williams Creativity Test B(WCTB) and Adolescent Scientific Creativity Scale(ASCS) were used to measure the creative affective and scientific creativity for 550 middle school students. The data was clustered with SOM neural network, and three categories were obtained. There were significant differences for creativity factors except imagination among the categories. In 550 students, 70% of them were used as modeling group, and the other as testing group. Generalized regression neural network (GRNN) and multivariable linear regression (MLR) were used for modeling and testing. Risk-taking curiosity, imagination and complexity scores used as input and independent variable, scientific creative scores used as output and dependent variable. The result showed the predictive error of GRNN was lower than the error of MLR. The neural networks could analyze creativity measurement data very well. © 2011 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Yu, J. (2011). The application of SOM and GRNN in creativity measurement for middle school students. In Advances in Intelligent and Soft Computing (Vol. 110, pp. 211–214). https://doi.org/10.1007/978-3-642-25185-6_28
Mendeley helps you to discover research relevant for your work.