DeepAI AI Chat
Log In Sign Up

Adaptive Explainable Neural Networks (AxNNs)

by   Jie Chen, et al.

While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the results. We develop a new framework called Adaptive Explainable Neural Networks (AxNN) for achieving the dual goals of good predictive performance and model interpretability. For predictive performance, we build a structured neural network made up of ensembles of generalized additive model networks and additive index models (through explainable neural networks) using a two-stage process. This can be done using either a boosting or a stacking ensemble. For interpretability, we show how to decompose the results of AxNN into main effects and higher-order interaction effects. The computations are inherited from Google's open source tool AdaNet and can be efficiently accelerated by training with distributed computing. The results are illustrated on simulated and real datasets.


GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions

The lack of interpretability is an inevitable problem when using neural ...

Explaining Models by Propagating Shapley Values of Local Components

In healthcare, making the best possible predictions with complex models ...

Explainable Neural Networks based on Additive Index Models

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

Explainable expected goal models for performance analysis in football analytics

The expected goal provides a more representative measure of the team and...

Constrained Generalized Additive 2 Model with Consideration of High-Order Interactions

In recent years, machine learning and AI have been introduced in many in...

Evaluating the Explainers: Black-Box Explainable Machine Learning for Student Success Prediction in MOOCs

Neural networks are ubiquitous in applied machine learning for education...

ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model

The need for interpretable models has fostered the development of self-e...