Corpus ID: 210839295

An interpretable neural network model through piecewise linear approximation

@article{Guo2020AnIN,
  title={An interpretable neural network model through piecewise linear approximation},
  author={Mengzhuo Guo and Qingpeng Zhang and Xiuwu Liao and Daniel Dajun Zeng},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.07119}
}
  • Mengzhuo Guo, Qingpeng Zhang, +1 author Daniel Dajun Zeng
  • Published in ArXiv 2020
  • Computer Science, Mathematics
  • Most existing interpretable methods explain a black-box model in a post-hoc manner, which uses simpler models or data analysis techniques to interpret the predictions after the model is learned. However, they (a) may derive contradictory explanations on the same predictions given different methods and data samples, and (b) focus on using simpler models to provide higher descriptive accuracy at the sacrifice of prediction accuracy. To address these issues, we propose a hybrid interpretable model… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES

    Hybrid Predictive Model: When an Interpretable Model Collaborates with a Black-box Model

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Chandan Singh

    • W James Murdoch
    • Karl Kumbier, Reza Abbasi-Asl, and Bin Yu. Interpretable machine learning: definitions, methods, and applications. arXiv preprint arXiv:1901.04592
    • 2019
    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Detecting Statistical Interactions from Neural Network Weights

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    In Proceedings of the 34th International Conference on Machine Learning-Volume 70

    • Avanti Shrikumar, Peyton Greenside, Anshul Kundaje. Learning important features through propa differences
    • pages 3145–3153. JMLR. org,
    • 2017
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    In Proceedings of the 34th International Conference on Machine Learning-Volume 70

    • Mukund Sundararajan, Ankur Taly, Qiqi Yan. Axiomatic attribution for deep networks
    • pages 3319–3328. JMLR. org,
    • 2017
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL