Research and application of Kernel convolutional neural networks

In this paper, using the advantages of kernel function nonlinear mapping, combined with convolutional neural network algorithms, a new network learning model kernel convolutional neural network(Kernel-CNN) is proposed.The method first preprocesses the data, and secondly uses the kernel convolutional neural network to extract the features of the data. Finally, the softmax classifier is constructed to classify the data.This network introduces the nonlinear mapping into the convolution process to form the kernel convolution process, and further enhances the feature extraction ability of the model through the kernel convolution operation.Experimental verification was performed on the MNIST handwritten digital library and the MIT-BIH arrhythmia database provided by the Massachusetts Institute of Technology. The correct rate of this model is 98.5% and 97%, respectively, which are better than convolutional neural networks and support vector machines. The model also has a small LOSS value.