Načítá se...
Stabilizing patterns in time: Neural network approach
Recurrent and feedback networks are capable of holding dynamic memories. Nonetheless, training a network for that task is challenging. In order to do so, one should face non-linear propagation of errors in the system. Small deviations from the desired dynamics due to error or inherent noise might ha...
Uloženo v:
| Vydáno v: | PLoS Comput Biol |
|---|---|
| Hlavní autoři: | , |
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
Public Library of Science
2017
|
| Témata: | |
| On-line přístup: | https://ncbi.nlm.nih.gov/pmc/articles/PMC5741269/ https://ncbi.nlm.nih.gov/pubmed/29232710 https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1371/journal.pcbi.1005861 |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!
|