Cargando…
MARGIN: Uncovering Deep Neural Networks Using Graph Signal Analysis
Interpretability has emerged as a crucial aspect of building trust in machine learning systems, aimed at providing insights into the working of complex neural networks that are otherwise opaque to a user. There are a plethora of existing solutions addressing various aspects of interpretability rangi...
Autores principales: | Anirudh, Rushil, Thiagarajan, Jayaraman J., Sridhar, Rahul, Bremer, Peer-Timo |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8320743/ https://www.ncbi.nlm.nih.gov/pubmed/34337397 http://dx.doi.org/10.3389/fdata.2021.589417 |
Ejemplares similares
-
Deep Graph Mapper: Seeing Graphs Through the Neural Lens
por: Bodnar, Cristian, et al.
Publicado: (2021) -
Auto-GNN: Neural architecture search of graph neural networks
por: Zhou, Kaixiong, et al.
Publicado: (2022) -
Graph Neural Networks for Charged Particle Tracking on FPGAs
por: Elabd, Abdelrahman, et al.
Publicado: (2022) -
Deep Graph Learning for Circuit Deobfuscation
por: Chen, Zhiqian, et al.
Publicado: (2021) -
TSI-GNN: Extending Graph Neural Networks to Handle Missing Data in Temporal Settings
por: Gordon, David, et al.
Publicado: (2021)