![]() |
![]() |
University of Birmingham > Talks@bham > Artificial Intelligence and Natural Computation seminars > Learning to identify software defects when historical sample modules are unavailable
Learning to identify software defects when historical sample modules are unavailableAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Leandro Minku. Host: Dr. Shan He Software Systems are becoming larger and more complex, which places a big challenge on software quality assurance because it is almost infeasible to conduct extensive code inspection or testing for every software module. Thus, constructing a predictor to identify the software modules that are likely to be defect-prone can enable a guided testing over those suspicious modules, which essentially help to find and fix more software defects under limited resource for testing. Machine learning is an effective way to construct a predictors from a large amount of historical sample modules. However, historical sample modules might not be always available or useful for identifying for defect patterns for a newly developed software project. In this case, how to learn an effective predictor to identify a defect-prone modules? In this talk, we will discuss the attempts to address this problem with advances in machine learning. This talk is part of the Artificial Intelligence and Natural Computation seminars series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsElectromagnetic Communications and Sensing Research Seminar Series IRLab Seminars: Robotics, Computer Vision & AI Quantitative Methods in Finance seminarOther talksWave turbulence in the Schrödinger-Helmholtz equation TBC TBA TBA Counting cycles in planar graphs Horizontal Mean Curvature Flow and stochastic optimal controls |