摘要
卷积神经网络(CNN)是一类包含卷积计算且具有深度结构的前馈神经网络,是深度学习的代表算法之一。卷积神经网络仿造生物的视知觉机制构建,可以进行监督学习和非监督学习,其隐含层内的卷积核参数共享和层间连接的稀疏性可以大程度上提升学习效率。基于此,将着重介绍卷积神经网络的基本结构,常见的激活函数和损失函数以及涉及的相关算法。
Convolution neural network(CNN)is a kind of feedforward neural network with deep structure and convolution computation,and it is one of the representative algorithms of deep learning.Convolutional neural network can simulate the visual perception mechanism of biology,and can be used for supervised learning and unsupervised learning.The sharing of convolutional kernel parameters in the hidden layer and the sparseness of interlayer connection can greatly improve the learning efficiency.Based on this,the basic structure of convolutional neural network,the common activation function and loss function as well as the related algorithms are introduced.
作者
王统
Wang Tong(China Three Gorges University,Chongqing 443002,China)
出处
《信息与电脑》
2020年第8期41-43,共3页
Information & Computer
关键词
卷积神经网络
权值共享
激活函数
损失函数
convolution neural network
weight sharing
activation function
loss function
