Optimization method of convolution neural network

Abstract

The invention discloses an optimization method of a convolution neural network. In a convolution neural network training process, a filter group with poorer effects and a filter group with better effects are selected out, and parts of coefficients in the filter group with poorer effects are replaced by parts of coefficients in the filter group with better effects, parameter update between convolution layer filters is achieved. After a modified network has been trained for a certain time, error magnitude generated by the network after and before the modification is compared, whether the previously achieved parameter update of the filters is valid or not, selection is performed in the two networks, and the network with good performance is used for following trainings. By continuously repeating the above processes, a network with better performance can be obtained through the training and the feature extraction ability of the network is improved compared with the traditional network.

Description

technical field [0001] The present invention relates to the field of convolutional neural network research, in particular to a convolutional neural network optimization method. Background technique [0002] Deep learning is a research hotspot in the field of artificial intelligence. In recent years, deep learning has made breakthroughs in the field of machine vision. Among various deep learning methods, the research results of convolutional neural network are the most prominent. Since Alex and others won the first place in the ILSVRC image recognition competition in 2012 with a clear performance advantage over traditional methods, convolutional neural networks have set off a research boom in the field of machine vision. The industry has also invested a lot of money to apply research results related to convolutional neural networks to products related to machine vision and artificial intelligence. Convolutional neural networks have had a profound impact on academic researc...

AI Technical Summary

Problems solved by technology

[0007] The invention provides a convolutional neural network optimization method, which solves the technical problem that the performance of the existing convolutional neural network cannot be further improved, realizes the optimization of the convolutional neural network, and improves the performance of the convolutional neural network. technical effect

Images