Cargando…

Correcting gradient-based interpretations of deep neural networks for genomics

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 seemingly arb...

Descripción completa

Detalles Bibliográficos
Autores principales: Majdandzic, Antonio, Rajesh, Chandana, Koo, Peter K.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10169356/
https://www.ncbi.nlm.nih.gov/pubmed/37161475
http://dx.doi.org/10.1186/s13059-023-02956-3