Convolutional neural network based on PReLUs-Softplus nonlinear excitation function
GAO Li-peng
ZHENG Hui
Abstract：Aiming at the problem that the expression ability and recognition effect of convolutional neural network ( CNN) are affected by the excitation function of convolutional layer, a new nonlinear excitation function PReLUs-Softplus was proposed and applied to the convolutional layer in neural network. The contrast experiments on the image recognition of both new neural network and neural network with the traditional excitation function were performed in MNIST and CIFAR-10 standard database. The results show that compared with the neural network with the traditional excitation function, the convolutional neural network with PReLUs-Softplus excitation function has faster convergence rate in the calculation of image recognition under different pooling methods, and can effectively reduce the recognition error rate.
Keywords：deep learningconvolutional neural networkexcitation functionpattern recognitionnonlinear mappingpoolingnetwork structureimage recognition
Publication Date：2018-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 54-59 )