Cargando…
Correspondence between neuroevolution and gradient descent
We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian white noise. Averaged over independent realizations of the lear...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Nature Publishing Group UK
2021
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8563972/ https://www.ncbi.nlm.nih.gov/pubmed/34728632 http://dx.doi.org/10.1038/s41467-021-26568-2 |