Quality Evaluation Model of Preschool Art Education Based on Deep Learning Theory

In order to solve the problem that the expression ability and generalization ability of shallow learning network to complex functions are limited, and to improve the accuracy of preschool art education quality evaluation, a preschool art education quality evaluation method based on deep learning network is proposed. Starting from the creation of preschool art education environment, the quality of preschool art education and children’s development, this paper constructs a preschool art education quality evaluation index system including three primary indicators and nine secondary indicators. Take the secondary index in the evaluation index system as the input of the deep learning network, optimize the weights of each layer of the deep learning network by using the unsupervised pre training model, determine the conditional probability distribution and joint probability distribution of each layer in the restricted Boltzmann machine based on the bottom-up unsupervised learning process, and the output layer optimizes the parameters of each layer according to the input DMOS value, Build a regression model between the abstract primary index and DMOS value, and predict and obtain the objective evaluation results of the quality of preschool art education according to the regression model.