self-explaining neural networks

**SENN** (Self-Explaining Neural Networks) are **neural networks architecturally designed to produce their own explanations alongside predictions** — generating interpretable concept representations and relevance scores that explain each prediction as a linear combination of meaningful concepts. **SENN Architecture** - **Concept Encoder**: $h(x) = [h_1(x), ldots, h_k(x)]$ — maps input to interpretable concepts. - **Relevance Parameterizer**: $ heta(x) = [ heta_1(x), ldots, heta_k(x)]$ — input-dependent relevance scores. - **Prediction**: $f(x) = sum_i heta_i(x) cdot h_i(x)$ — locally linear combination of concepts. - **Regularization**: Concepts are regularized to be interpretable (sparse, coherent, diverse). **Why It Matters** - **Built-In Explanation**: Every prediction comes with a decomposition into concepts × relevances. - **Locally Linear**: The prediction is interpretable as a locally linear model in concept space. - **No Post-Hoc**: Unlike LIME/SHAP, explanations are part of the model — not approximate post-hoc attributions. **SENNs** are **neural networks that explain themselves** — architecturally designed to decompose every prediction into interpretable components.