首页|New Machine Learning Research from Stanford University Outlined (Keeper: Automat ed Testing and Fixing of Machine Learning Software)
New Machine Learning Research from Stanford University Outlined (Keeper: Automat ed Testing and Fixing of Machine Learning Software)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on artificial intelligence is now available. According to news reporting originating from Stanford, Califo rnia, by NewsRx correspondents, research stated, “The increasing number of softw are applications incorporating machine learning (ML) solutions has led to the ne ed for testing techniques.” Financial supporters for this research include Nsf; Aro; Doe Early Career Award; Ceres Center For Unstoppable Computing, Uchicago Marian And Stuart Rice Researc h Award. The news editors obtained a quote from the research from Stanford University: “H owever, testing ML software requires tremendous human effort to design realistic and relevant test inputs and to judge software output correctness according to human common sense. Even when misbehavior is exposed, it is often unclear whethe r the defect is inside ML API or the surrounding code and how to fix the impleme ntation. This article tackles these challenges by proposing Keeper, an automated testing and fixing tool for ML software. The core idea of Keeper is designing p seudo-inverse functions that semantically reverse the corresponding ML task in a n empirical way and proxy common human judgment of real-world data. It incorpora tes these functions into a symbolic execution engine to generate tests. Keeper a lso detects code smells that degrade software performance.”
Stanford UniversityStanfordCaliforni aUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMac hine LearningSoftware
NETL
NSTL
