Transparency
40 techniques
Making AI systems and their decision-making processes open and understandable.
Browse by subcategory
All techniques
40 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... | ||
| DeepLIFT | Algorithmic | Requirements/model Internals Architecture/neural Networks +2 | Any | DeepLIFT (Deep Learning Important FeaTures) explains a single prediction of a neural network by dividing the difference... | ||
| Layer-wise Relevance Propagation | Algorithmic | Requirements/model Internals Architecture/neural Networks +3 | Any | Layer-wise Relevance Propagation (LRP) explains a neural network's prediction by working backwards from the output to... | ||
| Contextual Decomposition | Algorithmic | Architecture/neural Networks/recurrent Requirements/white Box +1 | Text | Contextual Decomposition explains why an LSTM, a neural network that reads text one word at a time, made a particular... | ||
| 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 | Tabular | A ridge regression surrogate approximates a complex model with a linear equation fitted to the complex model's own... | ||
| 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... | ||
| Differential Privacy | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | Differential privacy puts a mathematical limit on what a published result reveals about any one person. The data holder... | ||
| Conformal Prediction | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | Conformal prediction wraps any trained model so that, instead of a single answer, it returns a set of plausible answers... | ||
| Platt Scaling | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | Platt scaling turns a classifier's raw scores into calibrated probabilities, meaning that among the cases given a... | ||
| Temperature Scaling | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | Temperature scaling is a correction applied after training to a classifier that is more confident than it is accurate, a... | ||
| Deep Ensembles | Algorithmic | Architecture/neural Networks Paradigm/parametric +2 | Any | Deep ensembles estimate how uncertain a neural network's predictions are by training several copies of the same network... | ||
| Bootstrap Ensembles | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | Bootstrap ensembles estimate how much a model's predictions depend on the particular sample of data it was trained on.... | ||
| Jackknife Resampling | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | Jackknife resampling, also called leave-one-out resampling, shows how much a result computed from a dataset depends on... | ||
| Algorithm Review Boards | Process | Architecture/model Agnostic Requirements/black Box | Any | An algorithm review board, also called an AI ethics board or AI review board, is a standing group from different... | ||
| Human-in-the-Loop Safeguards | Process | Architecture/model Agnostic Requirements/black Box | Any | Human-in-the-loop safeguards hold an AI system's output at a checkpoint until a trained person has reviewed it.... | ||
| Confidence Thresholding | Algorithmic | Architecture/model Agnostic Requirements/black Box +1 | Any | Confidence thresholding uses a model score to decide whether a prediction should proceed automatically or receive... | ||
| Runtime Monitoring and Circuit Breakers | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | Runtime monitoring and circuit breakers observe a deployed AI service and restrict model calls when configured signals... |
Rows per page
Page 1 of 2