expertise needed
ml engineering
Requires machine learning engineering skills
86 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Integrated Gradients | Algorithmic | Architecture/neural Networks Paradigm/parametric +3 | Any | Integrated Gradients is an attribution technique that explains a model's prediction by quantifying the contribution of... | ||
| 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... | ||
| Taylor Decomposition | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Any | Taylor Decomposition is a mathematical technique that explains neural network predictions by computing first-order and... | ||
| Sobol Indices | Algorithmic | Architecture/model Agnostic Requirements/black Box | 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 | 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... | ||
| Partial Dependence Plots | Algorithmic | Architecture/model Agnostic Requirements/black Box | Any | Partial Dependence Plots show how changing one or two features affects a model's predictions on average. The technique... | ||
| Saliency Maps | Algorithmic | Architecture/neural Networks Requirements/differentiable +1 | Image | Saliency maps are visual explanations for image classification models that highlight which pixels in an image most... | ||
| Gradient-weighted Class Activation Mapping | Algorithmic | Architecture/neural Networks/convolutional Requirements/architecture Specific +2 | Image | Grad-CAM creates visual heatmaps showing which regions of an image a convolutional neural network focuses on when making... | ||
| Occlusion Sensitivity | Algorithmic | Architecture/model Agnostic Requirements/black Box | 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 | Architecture/neural Networks/recurrent Requirements/architecture Specific +1 | Any | Classical attention mechanisms in RNNs and CNNs create alignment matrices and temporal attention patterns that show how... | ||
| Prototype and Criticism Models | Algorithmic | Architecture/model Agnostic Paradigm/supervised +3 | Any | Prototype and Criticism Models provide data understanding by identifying two complementary sets of examples: prototypes... | ||
| Influence Functions | Algorithmic | Architecture/linear Models Architecture/neural Networks +6 | Any | Influence functions quantify how much each training example influenced a model's predictions by computing the change in... | ||
| 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... | ||
| Monte Carlo Dropout | Algorithmic | Architecture/neural Networks Paradigm/probabilistic +4 | Any | Monte Carlo Dropout estimates prediction uncertainty by applying dropout (randomly setting neural network weights to... | ||
| Out-of-Distribution Detector for Neural Networks | Algorithmic | Architecture/neural Networks Paradigm/discriminative +3 | Any | ODIN (Out-of-Distribution Detector for Neural Networks) identifies when a neural network encounters inputs significantly... | ||
| Adversarial Debiasing | Algorithmic | Architecture/neural Networks Paradigm/discriminative +4 | Any | Adversarial debiasing reduces bias by training models using a competitive adversarial setup, similar to Generative... | ||
| Counterfactual Fairness Assessment | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Any | Counterfactual Fairness Assessment evaluates whether a model's predictions would remain unchanged if an individual's... |
Rows per page
Page 1 of 5