Cargando…
Doing the Impossible: Why Neural Networks Can Be Trained at All
As deep neural networks grow in size, from thousands to millions to billions of weights, the performance of those networks becomes limited by our ability to accurately train them. A common naive question arises: if we have a system with billions of degrees of freedom, don't we also need billion...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Frontiers Media S.A.
2018
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6052125/ https://www.ncbi.nlm.nih.gov/pubmed/30050485 http://dx.doi.org/10.3389/fpsyg.2018.01185 |