The mythos of model interpretability-Reference-Cited by-同舟云学术

The mythos of model interpretability

Published:2018-09-26 Issue:10 Volume:61 Page:36-43
ISSN:0001-0782
Container-title:Communications of the ACM
language:en
Short-container-title:Commun. ACM

Author:

Lipton Zachary C.¹

Affiliation:

1. Carnegie Mellon University in Pittsburgh, PA

Abstract

In machine learning, the concept of interpretability is both important and slippery.

Publisher

Association for Computing Machinery (ACM)

Subject

General Computer Science

Link

https://dl.acm.org/doi/pdf/10.1145/3233231

Reference30 articles.

1. Athey S. and Imbens G.W. Machine-learning methodsm 2015; https://arxiv.org/abs/1504.01132v1. Athey S. and Imbens G.W. Machine-learning methodsm 2015; https://arxiv.org/abs/1504.01132v1.

2. Intelligible Models for HealthCare

Cited by 1146 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Opti-CAM: Optimizing saliency maps for interpretability;Computer Vision and Image Understanding;2024-11

2. A novel coupling interpretable machine learning framework for water quality prediction and environmental effect understanding in different flow discharge regulations of hydro-projects;Science of The Total Environment;2024-11

3. Differentiable self-supervised clustering with intrinsic interpretability;Neural Networks;2024-11

4. Machine learning-assisted design of high-entropy alloys with superior mechanical properties;Journal of Materials Research and Technology;2024-11

5. GNN-MgrPool: Enhanced graph neural networks with multi-granularity pooling for graph classification;Information Sciences;2024-10