Tracking Concept Change with Incremental Boosting by Minimization of the Evolving Exponential Loss
author: Mihajlo Grbovic, Center for Data Analytics and Biomedical Informatics, Temple University
published: Nov. 30, 2011, recorded: September 2011, views: 3315
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Fault localization, i.e., identifying erroneous lines of code in a buggy program, is a tedious process, which often requires considerable manual effort and is costly. Recent years have seen much progress in techniques for automated fault localization, specifically using program spectra - executions of failed and passed test runs provide a basis for isolating the faults. Despite the progress, fault localization in large programs remains a challenging problem, because even inspecting a small fraction of the lines of code in a large problem can require substantial manual effort. This paper presents a novel framework for fault localization based on latent divergences - an effective method for feature selection in machine learning. Our insight is that the problem of fault localization can be reduced to the problem of feature selection, where lines of code correspond to features. We also present an experimental evaluation of our framework using the Siemens suite of subject programs, which are a standard benchmark for studying fault localization techniques in software engineering. The results show that our framework enables more accurate fault localization than existing techniques.
Download slides: ecmlpkdd2011_grbovic_loss_01.pdf (1.5 MB)
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !
Write your own review or comment: