基于人工智能TensorFlow平台的建设与研究  

Construction and research of TensorFlow platform based on artificial intelligence

作　　者：潘文婵[1] 黄海平[1] PAN Wenchan;HUANG Haiping(School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210023,China)

机构地区：[1]南京邮电大学计算机学院,江苏南京210023

出　　处：《实验室科学》2023年第4期44-47,共4页Laboratory Science

基　　金：2021年国家自然科学基金(项目编号:62072252);南京邮电大学实验室工作研究课题(项目编号:2020XSG08)。

摘　　要：结合人工智能与大数据等相关专业,对人工智能TensorFlow平台的建设进行探讨。介绍图像识别算法,以及深度学习框架TensorFlow的工作原理,使用TensorFlow构建卷积神经网络实现CIFAR-10数据集分类,提高图像识别的准确率。建设人工智能TensorFlow平台,以大数据、机器学习、深度学习等学科为基础,推进人工智能教学、科研实践、创新服务的开展。新工科背景下对人工智能方向人才培养模式进行分析,以人工智能实验平台为载体,注重多学科交叉融合,培养复合型创新人才。Combined with artificial intelligence,big data and other related majors,this paper discusses the construction of artificial intelligence TensorFlow platform.This paper introduces the image recognition algorithm and the working principle of deep learning framework TensorFlow,and uses TensorFlow to construct convolutional neural network to realize the classification of CIFAR-10 data set,so as to improve the accuracy of image recognition.The construction of artificial intelligence TensorFlow platform,promotes the development of artificial intelligence teaching,scientific research practice and innovative services based on big data,machine learning,deep learning and other disciplines.Under the background of new engineering,the cultivation mode of talents in artificial intelligence direction is analyzed.With artificial intelligence experimental platform as the carrier,multi-disciplinary integration is emphasized to cultivate interdisciplinary and innovative talents.

关 键 词：人工智能 卷积神经网络 图像识别 深度学习 

分 类 号：G482[文化科学—教育学]