可微分抽象机混合编程系统
作者:
作者单位:

作者简介:

周鹏(1984-),男,河南信阳人,博士生,工程师,主要研究领域为机器学习,系统安全,操作系统与虚拟化;赵琛(1967-),男,博士,研究员,博士生导师,CCF高级会员,主要研究领域为编译技术,操作系统与网络软件;武延军(1979-),男,博士,研究员,博士生导师,CCF高级会员,主要研究领域为操作系统,系统安全.

通讯作者:

周鹏,E-mail:zhoupeng@iscas.ac.cn;武延军,E-mail:yanjun@iscas.ac.cn

中图分类号:

基金项目:

中国科学院战略性先导科技专项(Y8XD373105)


Hybrid Programming System of Differentiable Abstract Machines
Author:
Affiliation:

Fund Project:

Chinese Academy of Sciences Strategic Pilot Science and Technology Project (Y8XD373105)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    自动化编程是智能软件的核心挑战之一,使用程序执行轨迹或输入输出样例学习程序,是自动化编程的典型研究方法.这些方法无法弥合常规程序元素与神经网络组件间的隔阂,不能吸收经验信息输入、缺乏编程控制能力.给出了一种可无缝结合高级编程语言与神经网络组件的混合编程模型:使用高级编程语言元素和神经网络组件元素混合开发应用程序,其中,编程语言描述程序的框架、提供经验信息,关键复杂部分则用未定、可学习的神经网络组件占位,应用程序在可微分抽象机上运行生成程序的连续可微分计算图表示,然后使用输入输出数据,通过可微分优化方法对计算图进行训练,学习程序的未定部分,自动生成完整的确定性程序.可微分抽象机混合编程模型给出了一种能够将编程经验与神经网络自学习相结合的程序自动生成方法,弥合编程语言元素与神经网络元素间的隔阂,发挥并整合高级过程化编程和神经网络可训练学习编程各自的优势,将复杂的细节交给神经网络未定部分自动生成,降低编程难度或工作量,而适当的经验输入又有助于未定部分的学习,同时,为复用长期积累的宝贵编程经验提供输入接口.

    Abstract:

    Automated programming is one of the central challenges of intelligent software. Learning program by program execution traces or input output pairs are typical automatic programming research methods, but these methods can not bridge the gap between normal program elements and neural network components, can not absorb programing experience as input, and lack of programming control interface. This paper presents a hybrid programming model that seamlessly combines advanced programming language with neural network components. The program is composed of a mixture of elements from high-level programming language and neural network component, in which the language describes the sketch to provide experience information, with the key complex parts placed with undetermined and learnable neural network components. The program runs on differentiable abstraction machines to generate its continuous differentiable computational graph representation. Then, input-output pairs are used to train the graph by differentiable optimization method to learn to generate the complete program automaticly. This programming model provides an automatic program generation method which can combine programmer experience with neural network self-learning, bridges the gap between elements from programming language and neural network, which integrate the advantages of procedural and neural network programming, the complex details are automatically generated by neural networks to reduce the difficulty or workload of programming. Experience input is heuristic-helpful to the learning of undetermined parts and provides an input interface for reusing valuable programming experience accumulated over a long period of time.

    参考文献
    相似文献
    引证文献
引用本文

周鹏,武延军,赵琛.可微分抽象机混合编程系统.软件学报,2019,30(5):1224-1242

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2018-08-31
  • 最后修改日期:2018-10-31
  • 录用日期:
  • 在线发布日期: 2019-05-08
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号