Corpus ID: 212725443

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

@article{Yang2020GAMINetAE,
  title={GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions},
  author={Zebin Yang and Aijun Zhang and A. Sudjianto},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.07132}
}
  • Zebin Yang, Aijun Zhang, A. Sudjianto
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • The lack of interpretability is an inevitable problem when using neural network models in real applications. In this paper, a new explainable neural network called GAMI-Net, based on generalized additive models with structured interactions, is proposed to pursue a good balance between prediction accuracy and model interpretability. The GAMI-Net is a disentangled feedforward network with multiple additive subnetworks, where each subnetwork is designed for capturing either one main effect or one… CONTINUE READING
    Neural Mixture Distributional Regression
    Interpretable Machine Learning with an Ensemble of Gradient Boosting Machines
    Efficiently Training Intelligible Models for Global Explanations

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES
    Explainable Neural Networks based on Additive Index Models
    • 31
    • PDF
    Enhancing Explainability of Neural Networks through Architecture Constraints
    • 6
    • PDF
    A Unified Approach to Interpreting Model Predictions
    • 1,376
    • PDF
    A LASSO FOR HIERARCHICAL INTERACTIONS.
    • 312
    • Highly Influential
    • PDF
    Generalized Additive Models
    • 2,364
    • PDF
    Discovering additive structure in black box functions
    • 68
    • PDF
    From local explanations to global understanding with explainable AI for trees
    • 105
    "Why Should I Trust You?": Explaining the Predictions of Any Classifier
    • 3,234
    • PDF
    Detecting Statistical Interactions from Neural Network Weights
    • 60
    • PDF