Correcting gradient-based interpretations of deep neural networks for genomics

Correcting gradient-based interpretations of deep neural networks for genomics

Abstract Post hoc attribution methods can provide insights into the learned patterns from deep neural networks (DNNs) trained on high-throughput functional genomics data. However, in practice, their resultant attribution maps can be challenging to interpret due to spurious importance scores for seem...

Full description

Bibliographic Details
Main Authors: Antonio Majdandzic, Chandana Rajesh, Peter K. Koo
Format: Article
Language:English
Published: BMC 2023-05-01
Series:Genome Biology
Subjects:
Deep learning
Regulatory genomics
Model interpretability
Attribution methods
Explainable AI
Online Access:https://doi.org/10.1186/s13059-023-02956-3

Internet

https://doi.org/10.1186/s13059-023-02956-3

Similar Items