Jafarinejad, Foad ; Narasimhan, Krishna ; Mezini, Mira
Hrsg.: Wang, Shuai ; Xie, Xiaofei ; Ma, Lei (2021)
NerdBug: automated bug detection in neural networks.
30th ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA '21). virtual Conference (12.07.2021)
doi: 10.1145/3464968.3468409
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Despite the exponential growth of deep learning software during the last decade, there is a lack of tools to test and debug issues in deep learning programs. Current static analysis tools do not address challenges specific to deep learning as observed by past research on bugs specific to this area. Existing deep learning bug detection tools focus on specific issues like shape mismatches. In this paper, we present a vision for an abstraction-based approach to detect deep learning bugs and the plan to evaluate our approach. The motivation behind the abstraction-based approach is to be able to build an intermediate version of the neural network that can be analyzed in development time to provide live feedback programmers are used to with other kind of bugs.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2021 |
| Herausgeber: | Wang, Shuai ; Xie, Xiaofei ; Ma, Lei |
| Autor(en): | Jafarinejad, Foad ; Narasimhan, Krishna ; Mezini, Mira |
| Art des Eintrags: | Bibliographie |
| Titel: | NerdBug: automated bug detection in neural networks |
| Sprache: | Englisch |
| Publikationsjahr: | 11 Juli 2021 |
| Verlag: | ACM |
| Buchtitel: | AISTA 2021: Proceedings of the 1st ACM International Workshop on AI and Software Testing/Analysis |
| Veranstaltungstitel: | 30th ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA '21) |
| Veranstaltungsort: | virtual Conference |
| Veranstaltungsdatum: | 12.07.2021 |
| DOI: | 10.1145/3464968.3468409 |
| Kurzbeschreibung (Abstract): | Despite the exponential growth of deep learning software during the last decade, there is a lack of tools to test and debug issues in deep learning programs. Current static analysis tools do not address challenges specific to deep learning as observed by past research on bugs specific to this area. Existing deep learning bug detection tools focus on specific issues like shape mismatches. In this paper, we present a vision for an abstraction-based approach to detect deep learning bugs and the plan to evaluate our approach. The motivation behind the abstraction-based approach is to be able to build an intermediate version of the neural network that can be analyzed in development time to provide live feedback programmers are used to with other kind of bugs. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Softwaretechnik |
| TU-Projekte: | DFG|SFB1119|E1SFB1119 Mezini |
| Hinterlegungsdatum: | 01 Mär 2024 13:33 |
| Letzte Änderung: | 16 Mai 2024 07:45 |
| PPN: | 518323870 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum