Cargando…
A training algorithm for networks of high-variability reservoirs
Physical reservoir computing approaches have gained increased attention in recent years due to their potential for low-energy high-performance computing. Despite recent successes, there are bounds to what one can achieve simply by making physical reservoirs larger. Therefore, we argue that a switch...
Autores principales: | Freiberger, Matthias, Bienstman, Peter, Dambre, Joni |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7468150/ https://www.ncbi.nlm.nih.gov/pubmed/32879360 http://dx.doi.org/10.1038/s41598-020-71549-y |
Ejemplares similares
-
Simulating self-learning in photorefractive optical reservoir computers
por: Laporte, Floris, et al.
Publicado: (2021) -
Addressing limited weight resolution in a fully optical neuromorphic reservoir computing readout
por: Ma, Chonghuai, et al.
Publicado: (2021) -
Experimental results on nonlinear distortion compensation using photonic reservoir computing with a single set of weights for different wavelengths
por: Gooskens, Emmanuel, et al.
Publicado: (2023) -
Low-Loss Photonic Reservoir Computing with Multimode Photonic Integrated Circuits
por: Katumba, Andrew, et al.
Publicado: (2018) -
Highly parallel simulation and optimization of photonic circuits in time and frequency domain based on the deep-learning framework PyTorch
por: Laporte, Floris, et al.
Publicado: (2019)