Transparency

71 techniques

Making AI systems and their decision-making processes open and understandable.

71 techniques
GoalsModelsData TypesDescription
Coefficient Magnitudes (in Linear Models)
Metric
Architecture/linear Models
Paradigm/parametric
+2
Tabular
Coefficient Magnitudes assess feature influence in linear models by examining the absolute values of their coefficients....
DeepLIFT
Algorithmic
Architecture/neural Networks
Requirements/white Box
+1
Any
DeepLIFT (Deep Learning Important FeaTures) explains neural network predictions by decomposing the difference between...
Layer-wise Relevance Propagation
Algorithmic
Architecture/neural Networks
Paradigm/parametric
+2
Any
Layer-wise Relevance Propagation (LRP) explains neural network predictions by working backwards through the network to...
Contextual Decomposition
Algorithmic
Architecture/neural Networks/recurrent
Requirements/white Box
+1
Text
Contextual Decomposition explains LSTM and RNN predictions by decomposing the final hidden state into contributions from...
Local Interpretable Model-Agnostic Explanations
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
LIME (Local Interpretable Model-agnostic Explanations) explains individual predictions by approximating the complex...
Ridge Regression Surrogates
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
This technique approximates a complex model by training a ridge regression (a linear model with L2 regularisation) on...
Factor Analysis
Algorithmic
Architecture/model Agnostic
Paradigm/unsupervised
+1
Tabular
Factor analysis is a statistical technique that identifies latent variables (hidden factors) underlying observed...
Contrastive Explanation Method
Algorithmic
Architecture/neural Networks
Paradigm/discriminative
+4
Any
The Contrastive Explanation Method (CEM) explains model decisions by generating contrastive examples that reveal what...
ANCHOR
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
ANCHOR generates high-precision if-then rules that explain individual predictions by identifying the minimal set of...
RuleFit
Algorithmic
Architecture/model Agnostic
Paradigm/supervised
+1
Any
RuleFit creates interpretable surrogate models that can explain complex black-box models or serve as interpretable...
Differential Privacy
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
Differential privacy provides mathematically rigorous privacy protection by adding carefully calibrated random noise to...
Homomorphic Encryption
Algorithmic
Architecture/linear Models
Architecture/neural Networks/feedforward
+4
Any
Homomorphic encryption allows computation on encrypted data without decrypting it first, producing encrypted results...
Prediction Intervals
Algorithmic
Architecture/model Agnostic
Paradigm/supervised
+1
Any
Prediction intervals provide a range of plausible values around a model's prediction, expressing uncertainty as 'the...
Quantile Regression
Algorithmic
Architecture/linear Models/regression
Architecture/neural Networks
+4
Any
Quantile regression estimates specific percentiles (quantiles) of the target variable rather than just predicting the...
Conformal Prediction
Algorithmic
Architecture/model Agnostic
Requirements/black Box
Any
Conformal prediction provides mathematically guaranteed uncertainty quantification by creating prediction sets that...
Empirical Calibration
Algorithmic
Architecture/model Agnostic
Paradigm/supervised
+2
Any
Empirical calibration adjusts a model's predicted probabilities to match observed frequencies. For example, if events...
Temperature Scaling
Algorithmic
Architecture/neural Networks
Paradigm/discriminative
+3
Any
Temperature scaling adjusts a model's confidence by applying a single parameter (temperature) to its predictions. When a...
Deep Ensembles
Algorithmic
Architecture/neural Networks
Paradigm/parametric
+2
Any
Deep ensembles combine predictions from multiple neural networks trained independently with different random...
Bootstrapping
Algorithmic
Architecture/model Agnostic
Paradigm/supervised
+2
Any
Bootstrapping estimates uncertainty by repeatedly resampling the original dataset with replacement to create many new...
Jackknife Resampling
Algorithmic
Architecture/model Agnostic
Paradigm/supervised
+2
Any
Jackknife resampling (also called leave-one-out resampling) assesses model stability and uncertainty by systematically...
Rows per page
Page 1 of 4