Neural network construction system, method and storage medium of variable-length gene genetic algorithm

Abstract

The invention discloses a neural network construction system and method based on a variable-length genetic algorithm, wherein the construction system includes a sequentially connected training set generation module, a network initialization module, a network training module, a network update module, a network optimization module, Network selection module, iteration number update module and network generation module. The general idea of ​​the construction method of this scheme is to generate variable-length chromosomes in the initialization step, and randomly add BN components to specific genes of each chromosome. Through the training on the training set, the neural network structure representation corresponding to each chromosome is obtained through training, and the offspring chromosomes are selected. Subsequently, in the crossover step, the length of the crossed chromosomes is not fixed, and a growth and shrinking strategy is used to generate daughter chromosomes. Then use the traditional mutation and environment selection operations to complete the selection of offspring chromosomes, repeat the above, and decode the obtained best chromosomes into the corresponding neural network architecture.

Description

Technical field [0001] The present invention relates to a network structure of the search field of computer technology in depth study, in particular, to a construction system, method and storage medium based on neural networks becomes long genetic algorithm. Background technique [0002] With the development of deep learning, convolutional neural network (CNN) is widely used in computer vision tasks. Compared with the standard neural network, CNN CNN features sharing mechanism to help reduce the need to learn the right weight and the number of variables, which reduces network complexity, improve the image generalization. Thanks to medical data and engineering experts and well-designed the great efforts of CNN, for automatically analyzing CT images and to predict whether positive COVID-19 has made significant progress in reducing the burden of medical professional analysis of CT images. [0003] Although deep learning technology has been well developed, but to apply it COVID-19 in...

AI Technical Summary

Problems solved by technology

Therefore, the selection and setting of hyperparameters is a very complex and time-consuming task, which hinders the rapid application of deep learning methods

[0005] Second, there are few publicly available COVID-19 datasets

The neural network architecture designed based on these data sets will bring model bias, resulting in inaccurate application to other data sets

Images