DeepAI AI Chat
Log In Sign Up

Structural Neural Additive Models: Enhanced Interpretable Machine Learning

by   Mattias Luber, et al.

Deep neural networks (DNNs) have shown exceptional performances in a wide range of tasks and have become the go-to method for problems requiring high-level predictive power. There has been extensive research on how DNNs arrive at their decisions, however, the inherently uninterpretable networks remain up to this day mostly unobservable "black boxes". In recent years, the field has seen a push towards interpretable neural networks, such as the visually interpretable Neural Additive Models (NAMs). We propose a further step into the direction of intelligibility beyond the mere visualization of feature effects and propose Structural Neural Additive Models (SNAMs). A modeling framework that combines classical and clearly interpretable statistical methods with the predictive power of neural applications. Our experiments validate the predictive performances of SNAMs. The proposed framework performs comparable to state-of-the-art fully connected DNNs and we show that SNAMs can even outperform NAMs while remaining inherently more interpretable.


Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection

There is currently a large gap in performance between the statistically ...

Neural Additive Models: Interpretable Machine Learning with Neural Nets

Deep neural networks (DNNs) are powerful black-box predictors that have ...

Explainable Neural Networks based on Additive Index Models

Machine Learning algorithms are increasingly being used in recent years ...

Theory-based residual neural networks: A synergy of discrete choice models and deep neural networks

Researchers often treat data-driven and theory-driven models as two disp...

Scalable Interpretability via Polynomials

Generalized Additive Models (GAMs) have quickly become the leading choic...

Interpretable Deep Tracking

Imagine experiencing a crash as the passenger of an autonomous vehicle. ...