arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2301.09753cs.LGcs.SE
收藏

面向模块化机器学习解决方案开发:优点和权衡

Towards Modular Machine Learning Solution Development: Benefits and Trade-offs

University of Georgia(佐治亚大学)

Samiyuru Menik, Lakshmish Ramaswamy

摘要:

机器学习技术已经在各个领域展示了巨大的能力。他们在现代企业的成功中发挥着关键作用。然而,采用机器学习技术有很多未触及的潜力。开发解决独特业务问题的定制机器学习解决方案的成本是广泛采用机器学习技术的主要障碍。我们认识到,当今机器学习应用中普遍存在的整体性阻碍了高效且经济的定制机器学习解决方案开发。在这项工作中,我们探讨了模块化机器学习解决方案的好处,并讨论了模块化机器学习解决方案如何克服单片机器学习解决方案的一些主要解决方案工程限制。我们通过三个深度学习问题来分析模块化和单片机器学习解决方案之间的权衡;一个基于文本,两个基于图像。我们的实验结果表明,模块化机器学习解决方案具有很好的潜力,可以获得模块化的解决方案工程优势,同时以单片机器学习解决方案不允许的方式获得性能和数据优势。

英文摘要:

Machine learning technologies have demonstrated immense capabilities in various domains. They play a key role in the success of modern businesses. However, adoption of machine learning technologies has a lot of untouched potential. Cost of developing custom machine learning solutions that solve unique business problems is a major inhibitor to far-reaching adoption of machine learning technologies. We recognize that the monolithic nature prevalent in today's machine learning applications stands in the way of efficient and cost effective customized machine learning solution development. In this work we explore the benefits of modular machine learning solutions and discuss how modular machine learning solutions can overcome some of the major solution engineering limitations of monolithic machine learning solutions. We analyze the trade-offs between modular and monolithic machine learning solutions through three deep learning problems; one text based and the two image based. Our experimental results show that modular machine learning solutions have a promising potential to reap the solution engineering advantages of modularity while gaining performance and data advantages in a way the monolithic machine learning solutions do not permit.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑