Reliability
Shift Detection
Techniques that detect when inputs or conditions move outside what the model was built and tested for.
5 techniques
5 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Out-of-Distribution Detector for Neural Networks | Algorithmic | Architecture/neural Networks Paradigm/discriminative +3 | Image | ODIN (Out-of-Distribution Detector for Neural Networks) flags inputs that look unlike the data a neural network... | ||
| Runtime Monitoring and Circuit Breakers | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | Runtime monitoring and circuit breakers observe a deployed AI service and restrict model calls when configured signals... | ||
| Out-of-Domain Detection | Algorithmic | Architecture/model Agnostic Architecture/neural Networks/transformer/llm +2 | Text | Out-of-domain detection checks whether a user's query falls inside the topics and tasks a conversational AI system is... | ||
| Data Validation Checks | Testing | Architecture/model Agnostic Requirements/black Box | Tabular | Data validation checks apply a written set of rules about what valid data look like to every new batch of data before a... | ||
| Kernel Two-Sample Test (Maximum Mean Discrepancy) | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | A kernel two-sample test checks whether two sets of data could have come from the same distribution; in assurance it is... |
Rows per page
Page 1 of 1