Modeling of X-ray CT image by using revised GMDH-type neural networks with sigmoid functions
Tadashi Kondo, A.S. Pandya · 2004
In this paper, X-ray CT image is identified by using a revised GMDH-type neural network with sigmoid functions. The revised GMDH-type neural network algorithm with sigmoid functions proposed in this paper is developed based on the conventional GMDH-type neural network algorithm with a feedback loop. The revised GMDH-type neural networks can identify nonlinear complex systems very accurately because the complexity of the neural networks increase gradually by the feedback loop calculations and the structural parameters such as the number of neurons, the useful input variables and the number of feedback loop calculations are automatically determined so as to minimize the prediction error criterion defined as AIC.