HyDRA: hypergradient data relevance analysis for interpreting deep neural networks.

HyDRA: hypergradient data relevance analysis for interpreting deep neural networks.

The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HYDRA, which interprets the predictions made by DNNs as effects of their training data. Existing approaches generally estimate data con...

Full description

Bibliographic Details
Main Authors: Chen, Yuanyuan, Li, Boyang, Yu, Han, Wu, Pengcheng, Miao, Chunyan
Other Authors: School of Computer Science and Engineering
Format: Conference Paper
Language:English
Published: 2021
Subjects:
Engineering::Computer science and engineering
Interpretability
Neural Network
Machine Learning
Artificial Intelligence
Online Access:https://aaai.org/Conferences/AAAI-21/
https://hdl.handle.net/10356/147652

Internet

https://aaai.org/Conferences/AAAI-21/
https://hdl.handle.net/10356/147652

Similar Items