arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.05941cs.SEcs.AI
收藏

复合型AI的快速开发

Rapid Development of Compositional AI

MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室);IBM Research(IBM研究院)
Lee Martie, Jessie Rosenberg, Veronique Demers, Gaoyuan Zhang, Onkar Bhardwaj, John Henning, Aditya Prasad, Matt Stallone, Ja Young Lee, Lucy Yip, Damilola Ades… 展开作者

Lee Martie, Jessie Rosenberg, Veronique Demers, Gaoyuan Zhang, Onkar Bhardwaj, John Henning, Aditya Prasad, Matt Stallone, Ja Young Lee, Lucy Yip, Damilola Adesina, Elahe Paikari, Oscar Resendiz, Sarah Shaw, David Cox

摘要:

组合式人工智能系统将多个人工智能组件与其他应用程序组件结合在一起,以解决更大的问题,没有已知的开发模式,并且通常以定制和特设的方式进行处理。这使得开发速度更慢,更难在未来的应用程序中重用。为了支持组合式AI应用程序的整个快速开发周期,我们开发了一个名为(Bee)* 的新框架(以正则表达式的形式编写,发音为“beestar”)。我们展示了(Bee)* 如何通过简化的开发人员体验来支持构建集成、可扩展和交互式的组合AI应用程序。

英文摘要:

Compositional AI systems, which combine multiple artificial intelligence components together with other application components to solve a larger problem, have no known pattern of development and are often approached in a bespoke and ad hoc style. This makes development slower and harder to reuse for future applications. To support the full rapid development cycle of compositional AI applications, we have developed a novel framework called (Bee)* (written as a regular expression and pronounced as "beestar"). We illustrate how (Bee)* supports building integrated, scalable, and interactive compositional AI applications with a simplified developer experience.

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。

↑