摘要
随着人工智能(artificial intelligence,AI)的蓬勃发展,相应的机器学习方法也在不断取得新突破.本文通过对聊天机器人的发展进行回顾,梳理了人工智能和机器学习的基本研究现状,特别是依据任务及算法类型,依次介绍了在数据建模中常用的机器学习技术,包括监督学习、无监督学习、弱监督学习、强化学习和深度学习领域的典型方法或模型.本文最后还对机器学习的未来研究所面临的挑战和可研究方向进行了讨论.
With the vigorous development of Artificial Intelligence(AI),the corresponding machine learning methods are constantly making breakthroughs.By reviewing the development of chatbots,this paper sorts out the research status of AI and machine learning,especially according to tasks and algorithm types,and introduces machine learning technologies commonly used in data modeling,including typical methods or models in supervised learning,unsupervised learning,weakly supervised learning,reinforcement learning and deep learning.At the end of this paper,the challenges and possible research directions of machine learning are discussed.
作者
何思杰
刘庆芳
乔琛
HE Sijie;LIU Qingfang;QIAO Chen(School of Mathematics and Statistics,Xi'an Jiaotong University,Xi'an,Shaanxi 710049,China)
出处
《数学建模及其应用》
2023年第2期1-13,共13页
Mathematical Modeling and Its Applications
基金
国家自然科学基金重大项目(12090021)
国家自然科学基金(12271429)
陕西省自然科学基础研究计划(2022JM-005)
西安市科技创新计划(2019421315KYPT004JC006)。
关键词
数据建模
机器学习
人工智能
学习模型
data modeling
machine learning
artificial intelligence
learning model
