METHOD AND APPARATUS FOR MEASURING THIN FILM THICKNESS USING NEURAL NETWORK AND RECORD MEDIA THEREFOR

摘要

A method for measuring thickness of a thin film by using a neural network, and a device thereof are provided to minimize a thickness measuring error of the thin film by deciding the number of nodes for an input later and a concealed layer adequately. A method for measuring thickness of a thin film by using a neural network includes a step of collecting a reference reflection degree spectrum computed by a spectrometer for each reference object, a step of sampling the collected reference reflection degree spectrum by the pre-set number of patterns, a step of learning the neural network formed by the pre-set layer by using sampled data, and a step of estimating the thickness of the thin film for a sample by using the learned neural network(312). In a device for measuring the thickness of the thin film by using the neural network, the neural network is learned by using the reference reflection degree spectrum of the pre-set number of reference objects.