A Convolutional Neural Network Construction Method

Abstract

The invention discloses a method for constructing a convolutional neural network, which belongs to the technical field of neural networks. When the convolutional neural network is passed forward, on each original convolution kernel, the modulation of the original convolution kernel is realized through the dot product of the hand-tuned kernel and the original convolution kernel, and the modulated convolution kernel is obtained. The modulated convolution kernel replaces the original convolution kernel for the forward pass of the neural network to achieve the effect of feature enhancement. The method of the present invention greatly optimizes the neural network, so that the total number of kernels that the network must learn is reduced. In addition, the generation of sub-convolution kernels through modulation is used to arrange the redundant learning kernels in the original network structure, and the model can also be achieved. purpose of compression.

Description

technical field [0001] The invention relates to the technical fields of image recognition, artificial intelligence and neural network, in particular to a method for constructing a convolutional neural network. Background technique [0002] In recent years, with the emergence of ultra-large-scale classified data sets and parallel computing tools GPU, deep convolutional neural networks (deep convolution neural networks, DCNNs) have developed rapidly in the field of computer vision, and have received extensive attention from the academic community. This end-to-end network drives training through a large number of data training samples, and independently learns model parameters with the help of optimization algorithms such as stochastic gradient descent. A breakthrough has been made. [0003] The improvement of DCNNs performance depends on the expansion of training data and complex model structure. However, many practical problems in real life are usually only supported by smal...

AI Technical Summary

Problems solved by technology

In addition, traditional DCNNs usually have redundant learning convolution kernels during the training process. When the number of layers of the neural network increases, the data of the network will increase rapidly, so after training, the saved model will also take up a lot of storage space.

[0004] It can be seen that the deep convolutional neural network in the prior art has the problems of large training samples and consuming storage space

Images