Interpretable Neuron Structuring with Graph Spectral Regularization

While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making hidden layers more interpretable without significantly impacti...

Descripción completa

Detalles Bibliográficos
Autores principales: Tong, Alexander, van Dijk, David, Stanley, Jay S., Amodio, Matthew, Yim, Kristina, Muhle, Rebecca, Noonan, James, Wolf, Guy, Krishnaswamy, Smita
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8201816/
https://www.ncbi.nlm.nih.gov/pubmed/34131660
http://dx.doi.org/10.1007/978-3-030-44584-3_40

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8201816/
https://www.ncbi.nlm.nih.gov/pubmed/34131660
http://dx.doi.org/10.1007/978-3-030-44584-3_40

Ejemplares similares