Logo
Pattern

Discover published sets by community

Explore tens of thousands of sets crafted by our community.

Model Explainability and Interpretability

10

Flashcards

0/10

Still learning
StarStarStarStar

Anchors

StarStarStarStar

It provides high-precision rules, where changes to other features do not affect the prediction.

StarStarStarStar

Partial Dependence Plots (PDPs)

StarStarStarStar

They show the marginal effect of a feature on the predicted outcome of a model.

StarStarStarStar

Global Surrogate Models

StarStarStarStar

A globally interpretable model is trained to approximate the predictions of the black-box model.

StarStarStarStar

Feature Importance

StarStarStarStar

This technique ranks the features based on their importance in improving a model's prediction.

StarStarStarStar

Decision Tree Surrogates

StarStarStarStar

A decision tree is used to approximate the behavior of the black-box model, making it interpretable.

StarStarStarStar

LIME (Local Interpretable Model-agnostic Explanations)

StarStarStarStar

It provides local explanations by approximating the model locally with an interpretable one.

StarStarStarStar

SHAP (SHapley Additive exPlanations)

StarStarStarStar

It uses cooperative game theory to attribute the output change to each input feature's contribution fairly.

StarStarStarStar

Counterfactual Explanations

StarStarStarStar

They describe the smallest change to the input features that would change the prediction outcome.

StarStarStarStar

Individual Conditional Expectation (ICE) Plots

StarStarStarStar

They plot the relationship between the feature and the prediction for individual instances.

StarStarStarStar

Local Feature Importance

StarStarStarStar

Identifies the contribution of each feature to the prediction of a single instance.

Know
0
Still learning
Click to flip
Know
0
Logo

© Hypatia.Tech. 2024 All rights reserved.