Towards a More Reliable Interpretation of Machine Learning Outputs for Safety-Critical Systems using Feature Importance Fusion.
Divish RengasamyBenjamin RothwellGrazziela Patrocinio FigueredoPublished in: CoRR (2020)
Keyphrases
- safety critical
- machine learning
- safety analysis
- learning systems
- formal methods
- fault tolerant
- nuclear power plant
- agent architecture
- feature importance
- support systems
- feature selection
- embedded systems
- data mining
- text classification
- knowledge acquisition
- semi supervised
- artificial intelligence
- learning algorithm