Sign In

Communications of the ACM

ACM TechNews

Rice U. Turns Deep-Learning AI Loose on Software Development


Logo of the Bayou application

The new Bayou deep learning, software coding application aims to help programmers navigate growing numbers of application programming interfaces.

Credit: Rice University

Rice University researchers have invented Bayou, a deep learning, software coding application to help programmers navigate the mounting numbers of often-undocumented application programming interfaces (APIs).

"A developer can give Bayou a very small amount of information — just a few keywords or prompts, really — and Bayou will try to read the programmer's mind and predict the program they want," says Rice professor Swarat Chaudhuri.

Chaudhuri notes the app learned on its own by studying millions of lines of human-written Java code.

Rice professor Chris Jermaine says Bayou is especially useful for synthesizing examples of code for specific APIs. He also notes his team's chief goal is coaxing developers to extend Bayou, which has been issued under a permissive open source license.

"The more information we have about what people want from a system like Bayou, the better we can make it," Jermaine says. "We want as many people to use it as we can get."

From Rice University
View Full Article

 

Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA


 

No entries found