BAYOU learned to write code for programmers by studying billions of programs
Computer scientists at Rice University have created a deep-learning, software-coding application that can help human programmers navigate the growing multitude of often-undocumented application programming interfaces, or APIs.
Known as Bayou, the Rice application was created through an initiative funded by the Defense Advanced Research Projects Agency aimed at extracting knowledge from online source code repositories like GitHub. A paper on Bayou will be presented May 1 in Vancouver, British Columbia, at the Sixth International Conference on Learning Representations, a premier outlet for deep learning research. Users can try it out at askbayou.com.
Designing applications that can program computers is a long-sought grail of the branch of computer science called artificial intelligence (AI).
“People have tried for 60 years to build systems that can write code, but the problem is that these methods aren’t that good with ambiguity,” said Bayou co-creator Swarat Chaudhuri, associate professor of computer science at Rice. “You usually need to give a lot of details about what the target program does, and writing down these details can be as much work as just writing the code.”
“Bayou is a considerable improvement,” he said. “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.”
Chaudhuri said Bayou trained itself by studying millions of lines of human-written Java code. “It’s basically studied everything on GitHub, and it draws on that to write its own code.”
Bayou co-creator Chris Jermaine, a professor of computer science who co-directs Rice’s Intelligent Software Systems Laboratory with Chaudhuri, said Bayou is particularly useful for synthesizing examples of code for specific software APIs.
“Programming today is very different than it was 30 or 40 years ago,” Jermaine said. “Computers today are in our pockets, on our wrists and in billions of home appliances, vehicles and other devices. The days when a programmer could write code from scratch are long gone.”
Bayou architect Vijay Murali, a research scientist at the lab, said, “Modern software development is all about APls. These are system-specific rules, tools, definitions and protocols that allow a piece of code to interact with a specific operating system, database, hardware platform or another software system. There are hundreds of APIs, and navigating them is very difficult for developers. They spend lots of time at question-answer sites like Stack Overflow asking other developers for help.”
Murali said developers can now begin asking some of those questions at Bayou, which will give an immediate answer.
“That immediate feedback could solve the problem right away, and if it doesn’t, Bayou’s example code should lead to a more informed question for their human peers,” Murali said. Jermaine said the team’s primary goal is to get developers to try to extend Bayou, which has been released 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,” he said. “We want as many people to use it as we can get.”
Bayou is based on a method called neural sketch learning, which trains an artificial neural network to recognize high-level patterns in hundreds of thousands of Java programs. It does this by creating a “sketch” for each program it reads and then associating this sketch with the “intent” that lies behind the program.
When a user asks Bayou questions, the system makes a judgment call about what program it’s being asked to write. It then creates sketches for several of the most likely candidate programs the user might want.
“Based on that guess, a separate part of Bayou, a module that understands the low-level details of Java and can do automatic logical reasoning, is going to generate four or five different chunks of code,” Jermaine said. “It’s going to present those to the user like hits on a web search. ‘This one is most likely the correct answer, but here are three more that could be what you’re looking for.’”
The Latest on: Artificial intelligence and software development
via Google News
The Latest on: Artificial intelligence and software development
- Snapshot of the Emerging ICT Led Innovations in Artificial Intelligence, Machine Learning, Analytics, and Computer Visionon September 6, 2019 at 8:29 am
This provides a snapshot of the emerging ICT led innovations in Artificial Intelligence ... deployment/integration; track development of standards and software; and report on legislative and ...
- ICT sector development under the CPEC Framework is comprised on Artificial Intelligence- Shoaib Siddiquion September 6, 2019 at 12:05 am
ICT sector development under the CPEC Framework is comprised on Artificial Intelligence He further said that cooperation ... inflow and $16.2 million outflow during July 2019. Net FDI in software ...
- Artificial Intelligence in Manufacturing Market Expected to Reach CAGR of 55.2% by 2025on September 5, 2019 at 7:36 am
Artificial intelligence is a technology that deals with the study and enhancement of intelligent machines and software. This technology is used in industry verticals, such as manufacturing, supply ...
- Microgrids Made Easier — and Smarter — with Software that uses Artificial Intelligenceon September 5, 2019 at 6:39 am
Fortunately, artificial intelligence (AI) and machine learning (ML ... The Introspective Systems-Brightmerge microgrid software development project is governed under a contract Introspective Systems ...
- Ping An is Selected to Develop National Open Innovation Platform for Next Generation Artificial Intelligence in Consumer Puhui Financeon September 5, 2019 at 4:27 am
In the current announced batch, besides Ping An, nine other companies will be leading on nine other different development topics, including Underlying Software and Hardware (Huawei Technologies Co ...
- World Artificial Intelligence Conference 2019 (WAIC 2019)-a display of China leading AI achievementon September 5, 2019 at 12:00 am
World Artificial Intelligence Conference 2019 (WAIC 2019) in Shanghai just closed at the end of August. With the last day when it opened to the masses of visitors, it probably marked a critical point ...
- Continental continues to invest in artificial intelligenceon September 4, 2019 at 3:14 am
Cartica AI develops software in the field of artificial intelligence (AI). The solutions from Cartica ... Cartica AI working on rapid development of object recognition Continental already uses ...
- Artificial Intelligence-Based Security Market Recent Developments & Emerging Trends To 2028on September 4, 2019 at 2:07 am
Market Segments Covered In The Report: Segmentation by offering: Hardware, Software ... regional presence, and development opportunities are explained. Top Industry Players of Artificial ...
- ANSYS and Edge Case Research Transform Autonomous Vehicle Artificial Intelligenceon September 3, 2019 at 6:13 am
Through a new OEM agreement, Edge Case Research integrates its powerful AV artificial intelligence ... accelerating the development of safer, AI-driven perception software. Underlying capabilities ...
via Bing News