An investigation of challenges encountered when specifying training data and runtime monitors for safety critical ML applications.
Hans-Martin HeynEric KnaussIswarya MalleswaranShruthi DinakaranPublished in: CoRR (2023)
Keyphrases
- safety critical
- training data
- formal methods
- fault tolerant
- embedded systems
- safety analysis
- agent architecture
- nuclear power plant
- learning algorithm
- regulatory requirements
- support systems
- software agents
- adaptive systems
- information systems
- real time
- software systems
- knowledge based systems
- distributed systems
- databases