Cargando…
Multiplex visibility graphs to investigate recurrent neural network dynamics
A recurrent neural network (RNN) is a universal approximator of dynamical systems, whose performance often depends on sensitive hyperparameters. Tuning them properly may be difficult and, typically, based on a trial-and-error approach. In this work, we adopt a graph-based framework to interpret and...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
Nature Publishing Group
2017
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5345088/ https://www.ncbi.nlm.nih.gov/pubmed/28281563 http://dx.doi.org/10.1038/srep44037 |