摘要
深度学习理论是现代计算机机器学习中的非常重要的组成部分。计算机图形描述算法的实现解决了生成算法难的问题。研究了深度学习的理论:卷积神经网络和递归神经网络。结果表明:两种神经网络系统都能很好地处理图像的识别问题,对于计算机图形描述算法有着很好地辅助作用。同时,设计了一种基于卷积神经网络的计算机图形识别算法。实验结果表明:接收者操作特征(ROC)曲线和其面积的大小能够很好地判断计算机图形描述算法的准确性。
Deep learning theory is a very important part of modern computer machine learning.The realization of computer graphics description algorithm solves the problem of difficult algorithm generation.This article studies the theoryof deep learning,includingconvolutional neural networks and recurrent neural networks.The results show that both neural network systems can deal with image recognition well,and have a good auxiliary role for computer graphics description algorithms.At the same time,this paper designs a computer graphics recognition algorithm based on convolutional neural network.The experimental results show that the receiver operating characteristic(ROC)curve and its area can well judge the accuracy of the computer graphics description algorithm.
作者
邓卫军
DENG Weijun(School of Software,Hunan Vocational College of Science and Technology,Changsha 410000,China)
出处
《微型电脑应用》
2021年第2期53-55,共3页
Microcomputer Applications
基金
2017年度湖南省教育厅科学研究项目(17C07011)。
关键词
深度学习
卷积神经网络
递归神经网络
图形描述算法
deep learning
convolutional neural network
recurrent neural network
graphic description algorithm