Application of Improved Deep Belief Network Model in 3D Art Design

Abstract

In recent years, driven by the high-speed computing performance of computers and massive data on the Internet, deep nervine networks with highly abstract feature extraction and classification capabilities have been widely used in 3D art design and other fields, and a large number of breakthrough results have emerged. 3D art design is a research hotspot in the field of computer vision, which has broad application prospects and practical application value. Aiming at the problems of slow convergence and long training time of traditional deep belief network in the process of data feature expression, this paper proposes an unsupervised learning algorithm, namely adaptive deep belief network, and applies it to 3D art design. Its linear correction unit has good sparsity, which can improve the network performance well. The deep belief network DBN is formed by stacking the restricted Boltzmann machine RBM. The recognition research of 3D art design by optimizing the wavelet deep belief network can effectively improve the recognition rate and recognition speed of handwritten character recognition and achieve good results.