Cargando…

Theory and rationale of interpretable all-in-one pattern discovery and disentanglement system

In machine learning (ML), association patterns in the data, paths in decision trees, and weights between layers of the neural network are often entangled due to multiple underlying causes, thus masking the pattern-to-source relation, weakening prediction, and defying explanation. This paper presents...

Descripción completa

Detalles Bibliográficos
Autores principales: Wong, Andrew K. C., Zhou, Pei-Yuan, Lee, Annie E.-S.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10203344/
https://www.ncbi.nlm.nih.gov/pubmed/37217691
http://dx.doi.org/10.1038/s41746-023-00816-9