AIF-C01 notes
Responsible AI practices

Model Trade-Offs

Interpretability versus explainability

InterpretabilityExplainability
MeaningA human can explain the output directly from the model's weights and featuresThe behavior of any model, even a black box, is explained in human terms
HowInspect the inner mechanicsModel-agnostic methods: partial dependence plots, SHAP dependence plots, surrogate models
ExampleAn economist reads the coefficients of a regression model for inflationA news site discovers its neural network labels business articles about sports teams as "sports"

High interpretability usually costs performance. If you need exact transparency, your choice of algorithms is limited. If you need high performance with a general understanding, use explainability.

Safety versus transparency

Model safety is avoiding harm: bias, privacy exposure, and security vulnerabilities. Safety protects information and transparency exposes it, so they pull against each other:

  • Accuracy: complex neural networks are more accurate but less interpretable than linear models.
  • Privacy: techniques like differential privacy improve safety but make models harder to inspect.
  • Safety: filtering outputs hides the original reasoning.
  • Security: models trained on air-gapped networks are harder to audit externally.

Controllability

A controllable model is one whose predictions and behavior you can influence by changing the training data. It's more transparent and makes it easier to correct bias.

  • Linear models are more controllable than complex neural networks.
  • Test it by adding or removing examples and checking that the output changes as expected.
  • Improve it with data augmentation and training constraints.

On this page