Cargando…
Model-size reduction for reservoir computing by concatenating internal states through time
Reservoir computing (RC) is a machine learning algorithm that can learn complex time series from data very rapidly based on the use of high-dimensional dynamical systems, such as random networks of neurons, called “reservoirs.” To implement RC in edge computing, it is highly important to reduce the...
Autores principales: | Sakemi, Yusuke, Morino, Kai, Leleu, Timothée, Aihara, Kazuyuki |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7733507/ https://www.ncbi.nlm.nih.gov/pubmed/33311595 http://dx.doi.org/10.1038/s41598-020-78725-0 |
Ejemplares similares
-
Sequential patterns of spikes and scale-invariance in modular networks
por: Leleu, Timothee, et al.
Publicado: (2014) -
Oscillatory hierarchy in a network of leaky integrate-and-fire neurons with short-term plasticity
por: Leleu, Timothee, et al.
Publicado: (2013) -
Dynamical robustness in complex networks: the crucial role of low-degree nodes
por: Tanaka, Gouhei, et al.
Publicado: (2012) -
Computation of eigenmodes in long and complex accelerating structures by means of concatenation strategies
por: Flisgen, T, et al.
Publicado: (2014) -
Computation of Eigenmodes in Long and Complex Accelerating Structures by Means of Concatenation Strategies
por: Fligsen, T, et al.
Publicado: (2014)