Načítá se...

Dynamically Optimizing Network Structure Based on Synaptic Pruning in the Brain

Most neural networks need to predefine the network architecture empirically, which may cause over-fitting or under-fitting. Besides, a large number of parameters in a fully connected network leads to the prohibitively expensive computational cost and storage overhead, which makes the model hard to b...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Front Syst Neurosci
Hlavní autoři: Zhao, Feifei, Zeng, Yi
Médium: Artigo
Jazyk:Inglês
Vydáno: Frontiers Media S.A. 2021
Témata:
On-line přístup:https://ncbi.nlm.nih.gov/pmc/articles/PMC8220807/
https://ncbi.nlm.nih.gov/pubmed/34177473
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3389/fnsys.2021.620558
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!