A construction method of deep learning model comprising two CNNs

Abstract

The invention discloses a construction method of a new deep learning model, in particular to a deep learning model comprising two CNNs with different structures and converging quickly. The convolutionlayers of the two CNNs in the deep learning model constructed by the invention, convolution kernel size, The number of pooling layers and the full connection mode are different, and each CNN shares the feature information obtained from its learning once. Before sharing or accepting the feature information, the two CNNs undergo a batch normalization process. If the number of channels of the two CNNs is different when the feature information is shared, the number of channels is adjusted, and then the batch normalization process is performed. The current research direction of improving performance of deep learning model is to deepen the network deep of the model, The deep learning model provided by the invention improves the performance of the model, greatly accelerates the convergence speedof the network, reduces the parameters of the model, and reduces the serious dependence of the excellent deep learning model on the computer performance without constructing a deeper network.

Description

technical field [0001] The invention belongs to the field of deep learning, and specifically constructs a deep learning model that includes two convolutional neural networks with different structures and can quickly converge. Background technique [0002] The most important algorithm in the field of deep learning - Convolutional Neural Network (CNN), was first proposed in the middle and late 20th century. Although CNN has excellent performance in processing image data, it is limited by the storage capacity and computing power of computers at that time. The CNN algorithm has not received widespread attention from scholars. In the 21st century, the hardware foundation and computing power of computers have been qualitatively improved, and the complex CNN has a basis for realization. Many scholars have begun to engage in research on the application of CNN in complex image recognition. Studies have shown that the deeper the network of a deep learning model, the stronger its feat...

AI Technical Summary

Problems solved by technology

[0003] At present, the way to improve the performance of deep learning models is to deepen the convolutional layers of a single CNN, but as the number of convolutional layers increases, the network becomes difficult to train due to gradient disappearance or explosion.

Images