Deep learning network structure algorithm

Abstract

The invention discloses a deep learning network structure algorithm. The deep learning network structure algorithm includes the following steps when determining a connection relation among network layers: S101. collecting a subset of original data from data to be trained; S102. utilizing sample data to perform full-connection training; S103. setting a threshold value, and obtaining a sparse connection table; and S104. utilizing a new sparse connection table to calculate the original data. The deep learning network structure algorithm is suitable for the field of 3D printers, and is suitable for the field of deep learning algorithms. The deep learning network structure algorithm which can improve calculation efficiency and can also ensure calculation precision can be provided.

Description

technical field [0001] The invention relates to the technical field of deep learning algorithms, in particular to an adaptive sparse connection deep learning network structure algorithm. Background technique [0002] Deep learning is a new field in machine learning research. Its motivation is to establish and simulate the neural network of human brain for analysis and learning. It imitates the mechanism of human brain to explain data, such as images, sounds and texts. Its concept was proposed by Hinton et al. in 2006. Based on the deep belief network (DBN), a non-supervised greedy layer-by-layer training algorithm is proposed, which brings hope to solve the optimization problems related to the deep structure, and then a multi-layer autoencoder deep structure is proposed. In addition, the convolutional neural network proposed by Lecun et al. is the first real multi-layer structure learning algorithm, which uses the spatial relative relationship to reduce the number of parame...

AI Technical Summary

Problems solved by technology

However, the biggest drawback of this connection method is: the amount of calculation and memory consumption are huge, and the effici

Images