Korthals, Felix ; Stöcker, Marcel ; Rinderknecht, Stephan (2021)
Plausibility Assessment and Validation of Deep Learning Algorithms in Automotive Software Development.
doi: 10.1007/978-3-658-33466-6_7
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
The implementation of artificial intelligence (AI) systems in automotive software development still is an obstacle. Despite of accelerating scientific research and big wins in this field, the practical application is only possible in restricted environments or non safety critical components. There is a need to develop methods to verify the robustness and safety of AI software modules. The data based generation of deep learning (DL) algorithms creates black box models, which properties inhibit a validation as it is done for deterministic algorithms following ISO 26262. This paper introduces methods to assess the plausibility of AI model outputs. A description of the training data domains for a robust training is accomplished by means of one-class support vector machines (OCSVMs). This anomaly detection process encloses valid data within a DB, to be able to verify model outputs during operation. A further categorization of the training data domain into 20, equally spaced sub-domains led to best results in detecting implausible model calculations.
| Typ des Eintrags: |
Konferenzveröffentlichung
|
| Erschienen: |
2021 |
| Autor(en): |
Korthals, Felix ; Stöcker, Marcel ; Rinderknecht, Stephan |
| Art des Eintrags: |
Bibliographie |
| Titel: |
Plausibility Assessment and Validation of Deep Learning Algorithms in Automotive Software Development |
| Sprache: |
Englisch |
| Publikationsjahr: |
14 Mai 2021 |
| Ort: |
Wiesbaden |
| Verlag: |
Springer Vieweg |
| Buchtitel: |
21. Internationales Stuttgarter Symposium : Automobil- und Motorentechnik : Stuttgart 14.05.2021 |
| DOI: |
10.1007/978-3-658-33466-6_7 |
| URL / URN: |
https://link.springer.com/chapter/10.1007/978-3-658-33466-6_... |
| Kurzbeschreibung (Abstract): |
The implementation of artificial intelligence (AI) systems in automotive software development still is an obstacle. Despite of accelerating scientific research and big wins in this field, the practical application is only possible in restricted environments or non safety critical components. There is a need to develop methods to verify the robustness and safety of AI software modules. The data based generation of deep learning (DL) algorithms creates black box models, which properties inhibit a validation as it is done for deterministic algorithms following ISO 26262. This paper introduces methods to assess the plausibility of AI model outputs. A description of the training data domains for a robust training is accomplished by means of one-class support vector machines (OCSVMs). This anomaly detection process encloses valid data within a DB, to be able to verify model outputs during operation. A further categorization of the training data domain into 20, equally spaced sub-domains led to best results in detecting implausible model calculations. |
| Schlagworte: |
| Einzelne Schlagworte | Sprache |
|---|
| Machine Learning, Plausibility Assessment, Data Domain, One-Class Support, Vector Machine | nicht bekannt |
|
| Fachbereich(e)/-gebiet(e): |
16 Fachbereich Maschinenbau
16 Fachbereich Maschinenbau > Institut für Mechatronische Systeme im Maschinenbau (IMS) |
| Hinterlegungsdatum: |
23 Jun 2021 05:17 |
| Letzte Änderung: |
23 Jun 2021 05:17 |
| PPN: |
|
| Schlagworte: |
| Einzelne Schlagworte | Sprache |
|---|
| Machine Learning, Plausibility Assessment, Data Domain, One-Class Support, Vector Machine | nicht bekannt |
|
| Export: |
|
| Suche nach Titel in: |
TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum