Neural Additive Models (NAMs) make restrictions on the structure of neural networks, which yields a family of models that are inherently interpretable while suffering little loss in prediction accuracy when applied to tabular data. Methodologically, NAMs belong to a larger model family called Generalized Additive Models (GAMs).
NAMs learn a linear combination of networks that each attend to a single input feature: each $f_{i}$ in the traditional GAM formulationis parametrized by a neural network. These networks are trained jointly using backpropagation and can learn arbitrarily complex shape functions. Interpreting NAMs is easy as the impact of a feature on the prediction does not rely on the other features and can be understood by visualizing its corresponding shape function (e.g., plotting $f_{i}\left(x_{i}\right)$ vs. $x_{i}$).
Source: Neural Additive Models: Interpretable Machine Learning with Neural NetsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Additive models | 6 | 24.00% |
Interpretable Machine Learning | 3 | 12.00% |
BIG-bench Machine Learning | 3 | 12.00% |
Survival Analysis | 2 | 8.00% |
Decision Making | 2 | 8.00% |
Explainable Models | 1 | 4.00% |
Image Segmentation | 1 | 4.00% |
Semantic Segmentation | 1 | 4.00% |
Classification | 1 | 4.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |