Cargando…
Three learning stages and accuracy–efficiency tradeoff of restricted Boltzmann machines
Restricted Boltzmann Machines (RBMs) offer a versatile architecture for unsupervised machine learning that can in principle approximate any target probability distribution with arbitrary accuracy. However, the RBM model is usually not directly accessible due to its computational complexity, and Mark...
Autores principales: | Dabelow, Lennart, Ueda, Masahito |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9482660/ https://www.ncbi.nlm.nih.gov/pubmed/36115845 http://dx.doi.org/10.1038/s41467-022-33126-x |
Ejemplares similares
-
Temperature based Restricted Boltzmann Machines
por: Li, Guoqi, et al.
Publicado: (2016) -
Privacy-Preserving Restricted Boltzmann Machine
por: Li, Yu, et al.
Publicado: (2014) -
Using Memristors for Robust Local Learning of Hardware Restricted Boltzmann Machines
por: Ernoult, Maxence, et al.
Publicado: (2019) -
Thermodynamics of the Ising Model Encoded in Restricted Boltzmann Machines
por: Gu, Jing, et al.
Publicado: (2022) -
Entropy, Free Energy, and Work of Restricted Boltzmann Machines
por: Oh, Sangchul, et al.
Publicado: (2020)