On Sequential Bayesian Inference for Continual Learning

Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks. We revisit sequential Bayesian inference and assess whether using the previous task’s posterior as a prior for a new task can pr...

Descripción completa

Detalles Bibliográficos
Autores principales: Kessler, Samuel, Cobb, Adam, Rudner, Tim G. J., Zohren, Stefan, Roberts, Stephen J.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10297370/
https://www.ncbi.nlm.nih.gov/pubmed/37372228
http://dx.doi.org/10.3390/e25060884

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10297370/
https://www.ncbi.nlm.nih.gov/pubmed/37372228
http://dx.doi.org/10.3390/e25060884

Ejemplares similares