Abstract | ||
---|---|---|
ABSTRACTDeep Learning (DL) systems are key enablers for engineering intelligent applications. Nevertheless, using DL systems in safety- and security-critical applications requires to provide testing evidence for their dependable operation. We introduce DeepImportance, a systematic testing methodology accompanied by an Importance-Driven (IDC) test adequacy criterion for DL systems. Applying IDC enables to establish a layer-wise functional understanding of the importance of DL system components and use this information to assess the semantic diversity of a test set. Our empirical evaluation on several DL systems and across multiple DL datasets demonstrates the usefulness and effectiveness of DeepImportance. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1145/3377812.3390793 | International Conference on Software Engineering |
Keywords | DocType | ISSN |
Deep Learning Systems,Test Adequacy,Safety-Critical Systems | Conference | 0270-5257 |
ISBN | Citations | PageRank |
978-1-7281-6519-6 | 0 | 0.34 |
References | Authors | |
19 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simos Gerasimou | 1 | 110 | 14.31 |
Hasan Ferit Eniser | 2 | 13 | 3.56 |
Alper Sen | 3 | 278 | 36.73 |
Alper Cakan | 4 | 0 | 0.34 |