Cargando…
Model architecture can transform catastrophic forgetting into positive transfer
The work of McCloskey and Cohen popularized the concept of catastrophic interference. They used a neural network that tried to learn addition using two groups of examples as two different tasks. In their case, learning the second task rapidly deteriorated the acquired knowledge about the previous on...
| Autor principal: | |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Nature Publishing Group UK
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9232654/ https://www.ncbi.nlm.nih.gov/pubmed/35750768 http://dx.doi.org/10.1038/s41598-022-14348-x |