Convolutional neural network training method and target identification method and device

Abstract

The invention discloses a convolutional neural network training method and a target identification method and device. According to the convolutional neural network training method, on the one hand, a convolutional neural network convolutes data on different signal channels separately on the basis of the signal channels, and due to the differences of different signal channels, trained neuron convolution kernels are different from each other, so that the identification level of the convolutional neural network can be enhanced compared with the prior art; on the other hand, the convolutional neural network performs dropout on the basis of the signal channels during a forward transmission process and an object recognition process, the number of neurons keeps unchanged, so that data of all the channels of local receptive fields can be disposed. Therefore, the convolutional neural network training method can enhance the identification level of the convolutional neural network.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence and pattern recognition, in particular to a convolutional neural network training method, a convolutional neural network-based target recognition method and a device. Background technique [0002] Convolutional Neural Network (CNN) is an efficient recognition method that has been developed in recent years and has attracted widespread attention. Now, CNN has become one of the research hotspots in many scientific fields, especially in the field of pattern classification, because the network avoids the complex preprocessing of images and can directly input original images, so it has been more widely used. [0003] Generally, the basic structure of CNN includes multiple convolutional layers, and each convolutional layer is equipped with multiple neurons, and the input of each neuron is connected to the local receptive field of the previous convolutional layer. , by performing ...

AI Technical Summary

Problems solved by technology

[0012] However, since the dropout technology randomly selects neurons not to participate in training, the information of all channels in the image area corresponding to some neurons is lost, which is very likely to reduce the recognition degree of the deep convolutional neural network.

Images