Transparency
52 techniques
Making AI systems and their decision-making processes open and understandable.
52 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| 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.... | ||
| 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... | ||
| 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... | ||
| Factor Analysis | Algorithmic | Model Agnostic | Tabular | Factor analysis is a statistical technique that identifies latent variables (hidden factors) underlying observed... | ||
| Contrastive Explanation Method | Algorithmic | Model Agnostic | Any | The Contrastive Explanation Method (CEM) explains model decisions by generating contrastive examples that reveal what... | ||
| ANCHOR | Algorithmic | Model Agnostic | Any | ANCHOR generates high-precision if-then rules that explain individual predictions by identifying the minimal set of... | ||
| RuleFit | Algorithmic | Model Agnostic | Any | RuleFit is a method that creates an interpretable model by combining linear terms with decision rules. It first extracts... | ||
| Differential Privacy | Algorithmic | Model Agnostic | Any | Differential privacy provides mathematically rigorous privacy protection by adding carefully calibrated random noise to... | ||
| Homomorphic Encryption | Algorithmic | Model Agnostic | Any | Homomorphic encryption allows computation on encrypted data without decrypting it first, producing encrypted results... | ||
| Prediction Intervals | Algorithmic | Model Agnostic | Any | Prediction intervals provide a range of plausible values around a model's prediction, expressing uncertainty as 'the... | ||
| Quantile Regression | Algorithmic | Model Agnostic | Any | Quantile regression estimates specific percentiles (quantiles) of the target variable rather than just predicting the... | ||
| Conformal Prediction | Algorithmic | Model Agnostic | Any | Conformal prediction provides mathematically guaranteed uncertainty quantification by creating prediction sets that... | ||
| Empirical Calibration | Algorithmic | Model Agnostic | Any | Empirical calibration adjusts a model's predicted probabilities to match observed frequencies. For example, if events... | ||
| Temperature Scaling | Algorithmic | Neural Network | Any | Temperature scaling adjusts a model's confidence by applying a single parameter (temperature) to its predictions. When a... | ||
| Deep Ensembles | Algorithmic | Neural Network | Any | Deep ensembles combine predictions from multiple neural networks trained independently with different random... | ||
| Bootstrapping | Algorithmic | Model Agnostic | Any | Bootstrapping estimates uncertainty by repeatedly resampling the original dataset with replacement to create many new... | ||
| Jackknife Resampling | Algorithmic | Model Agnostic | Any | Jackknife resampling (also called leave-one-out resampling) assesses model stability and uncertainty by systematically... |
Rows per page
Page 1 of 3