Explainability

39 techniques

Understanding how AI systems make decisions and what factors influence their outputs.

39 techniques

		Models	Data Types	Description
SHapley Additive exPlanations	Algorithmic	Model Agnostic	Any	SHAP explains model predictions by quantifying how much each input feature contributes to the outcome. It assigns an...
Permutation Importance	Algorithmic	Model Agnostic	Any	Permutation Importance quantifies a feature's contribution to a model's performance by randomly shuffling its values and...
Mean Decrease Impurity	Algorithmic	Tree Based	Tabular	Mean Decrease Impurity (MDI) quantifies a feature's importance in tree-based models (e.g., Random Forests, Gradient...
Coefficient Magnitudes (in Linear Models)	Metric	Linear Model	Tabular	Coefficient Magnitudes assess feature influence in linear models by examining the absolute values of their coefficients....
Integrated Gradients	Algorithmic	Neural Network	Any	Integrated Gradients is an attribution technique that explains a model's prediction by quantifying the contribution of...
DeepLIFT	Algorithmic	Neural Network	Any	DeepLIFT (Deep Learning Important FeaTures) explains neural network predictions by decomposing the difference between...
Layer-wise Relevance Propagation	Algorithmic	Neural Network	Any	Layer-wise Relevance Propagation (LRP) explains neural network predictions by working backwards through the network to...
Contextual Decomposition	Algorithmic	Recurrent Neural Network	Text	Contextual Decomposition explains LSTM and RNN predictions by decomposing the final hidden state into contributions from...
Taylor Decomposition	Algorithmic	Neural Network CNN	Any	Taylor Decomposition is a mathematical technique that explains neural network predictions by computing first-order and...
Sobol Indices	Algorithmic	Model Agnostic	Any	Sobol Indices quantify how much each input feature contributes to the total variance in a model's predictions through...
Local Interpretable Model-Agnostic Explanations	Algorithmic	Model Agnostic	Any	LIME (Local Interpretable Model-agnostic Explanations) explains individual predictions by approximating the complex...
Ridge Regression Surrogates	Algorithmic	Model Agnostic	Any	This technique approximates a complex model by training a ridge regression (a linear model with L2 regularization) on...
Partial Dependence Plots	Algorithmic	Model Agnostic	Any	Partial Dependence Plots show how changing one or two features affects a model's predictions on average. The technique...
Individual Conditional Expectation Plots	Visualization	Model Agnostic	Any	ICE plots display the predicted output for individual instances as a function of a feature, with all other features held...
Saliency Maps	Algorithmic	Neural Network	Image	Saliency maps are visual explanations for image classification models that highlight which pixels in an image most...
Gradient-weighted Class Activation Mapping	Algorithmic	CNN	Image	Grad-CAM creates visual heatmaps showing which regions of an image a convolutional neural network focuses on when making...
Occlusion Sensitivity	Algorithmic	Model Agnostic	Image	Occlusion sensitivity tests which parts of the input are important by occluding (masking or removing) them and seeing...
Classical Attention Analysis in Neural Networks	Algorithmic	Rnn CNN	Any	Classical attention mechanisms in RNNs and CNNs create alignment matrices and temporal attention patterns that show how...
Factor Analysis	Algorithmic	Model Agnostic	Tabular	Factor analysis is a statistical technique that identifies latent variables (hidden factors) underlying observed...
Principal Component Analysis	Algorithmic	Model Agnostic	Any	Principal Component Analysis transforms high-dimensional data into a lower-dimensional representation by finding the...

Rows per page

Page 1 of 2

← Back to all categories