Explainability
Comprehensibility
Produces human-understandable formats
19 techniques in this subcategory
19 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Coefficient Magnitudes (in Linear Models) | Metric | Architecture/linear Models Paradigm/parametric +2 | Tabular | Coefficient Magnitudes explains a linear model by reading its fitted coefficients. Each coefficient shows how much the... | ||
| Ridge Regression Surrogates | Algorithmic | Architecture/model Agnostic Requirements/black Box | Tabular | A ridge regression surrogate approximates a complex model with a linear equation fitted to the complex model's own... | ||
| Partial Dependence Plots | Visualisation | Architecture/model Agnostic Requirements/black Box | Tabular | Partial Dependence Plots show how changing one or two features affects a model's predictions on average. The technique... | ||
| Gradient Saliency | Algorithmic | Architecture/neural Networks Requirements/differentiable +2 | Image | Gradient saliency (also called vanilla gradient saliency) is the simplest gradient-based explanation for image... | ||
| Gradient-weighted Class Activation Mapping | Algorithmic | Architecture/neural Networks/convolutional Requirements/architecture Specific +3 | Image | Grad-CAM (Gradient-weighted Class Activation Mapping) draws a heatmap over an image showing which regions most raise a... | ||
| Factor Analysis | Algorithmic | Architecture/model Agnostic Paradigm/unsupervised +1 | Tabular | Factor analysis looks for a small number of hidden factors that explain why a larger set of measured variables, such as... | ||
| Principal Component Analysis | Algorithmic | Architecture/model Agnostic Paradigm/unsupervised +1 | Any | Principal component analysis (PCA) summarises a dataset that has many numeric features by finding a few new axes along... | ||
| t-SNE | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | t-SNE (t-distributed Stochastic Neighbour Embedding) turns high-dimensional data into a two- or three-dimensional map... | ||
| Prototype and Criticism Models | Algorithmic | Architecture/model Agnostic Paradigm/supervised +2 | Any | Prototype and criticism methods summarise a dataset with a small set of real examples. Prototypes are instances chosen... | ||
| Contrastive Explanation Method | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | The Contrastive Explanation Method (CEM) explains one prediction of a classifier, such as a neural network, by... | ||
| ANCHOR | Algorithmic | Architecture/model Agnostic Requirements/black Box | Tabular | ANCHOR explains one prediction of a black-box classifier with an if-then rule, called an anchor, such as 'age > 30 AND... | ||
| RuleFit | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Tabular | RuleFit builds a predictive model that a person can read: a short list of if-then rules plus a few ordinary feature... | ||
| Generalized Additive Models | Algorithmic | Architecture/linear Models/gam Paradigm/parametric +2 | Tabular | A generalised additive model (GAM) builds its prediction by adding a baseline and one smooth curve for each input... | ||
| Neuron Activation Analysis | Algorithmic | Architecture/neural Networks Requirements/model Internals +1 | Text | Neuron activation analysis examines when individual neurons in a neural network respond strongly. The analyst runs a set... | ||
| Concept Activation Vectors | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Any | A concept activation vector (CAV) is a direction inside a neural network that stands for a human idea such as 'stripes'.... | ||
| Sparse Autoencoder Feature Analysis | Algorithmic | Architecture/neural Networks/transformer Architecture/neural Networks/transformer/llm +2 | Text | Sparse autoencoder feature analysis looks for human-interpretable units inside a neural network, usually a language... | ||
| Explanation Satisfaction Scale | Metric | Architecture/model Agnostic Requirements/black Box | Any | The Explanation Satisfaction Scale is a short questionnaire on which people who have used an AI system's explanations... | ||
| Forward Simulation Test | Testing | Architecture/model Agnostic Requirements/black Box | Any | A forward simulation test checks whether people who have studied a model's explanations can predict the model's output... | ||
| Think-Aloud Study of Explanation Use | Testing | Architecture/model Agnostic Requirements/black Box | Any | A think-aloud study of explanation use asks a small number of participants to say what they are thinking while they use... |
Rows per page
Page 1 of 1