Multi-scale Hybrid Pooling Convolutional Neural Network Algorithm

Nan ZHAO, Xin WANG, Ying-na LI, Sheng WU
2018 DEStech Transactions on Engineering and Technology Research  
With the popularization of the modern Internet and the rise of the mobile Internet, the data content of computer processing is more and more diverse. In this paper, we propose a multi-scale hybrid pooling algorithm based on convolutional neural network model, through convolution. The layer convolution method and the pooling mechanism of the pooling layer are improved to improve the generalization ability of the overall model. Learning Algorithm Principle and Description The Multi-scale Hybrid
more » ... oling Convolutional Neural Network (MSHP-CNN) model proposed in this chapter is an improved model based on the CNN model. The model is also the same in the structure of the network model. It is composed of input layer I, convolution layer C, pooling layer P, full connection layer F and output layer O, as shown inFigure1-1:
doi:10.12783/dtetr/ecar2018/26369 fatcat:zqjzqpmrbjagveug5nxfgfddnu