| Autor: |
Sälzer, Marco, Alsmann, Eric, Bruse, Florian, Lange, Martin |
| Rok vydání: |
2022 |
| Předmět: |
|
| Druh dokumentu: |
Working Paper |
| Popis: |
Verifying properties and interpreting the behaviour of deep neural networks (DNN) is an important task given their ubiquitous use in applications, including safety-critical ones, and their black-box nature. We propose an automata-theoric approach to tackling problems arising in DNN analysis. We show that the input-output behaviour of a DNN can be captured precisely by a (special) weak B\"uchi automaton and we show how these can be used to address common verification and interpretation tasks of DNN like adversarial robustness or minimum sufficient reasons. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
