Cargando…
An adiabatic method to train binarized artificial neural networks
An artificial neural network consists of neurons and synapses. Neuron gives output based on its input according to non-linear activation functions such as the Sigmoid, Hyperbolic Tangent (Tanh), or Rectified Linear Unit (ReLU) functions, etc.. Synapses connect the neuron outputs to their inputs with...
Autores principales: | Zhao, Yuansheng, Xiao, Jiang |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8492711/ https://www.ncbi.nlm.nih.gov/pubmed/34611220 http://dx.doi.org/10.1038/s41598-021-99191-2 |
Ejemplares similares
-
Synaptic metaplasticity in binarized neural networks
por: Laborieux, Axel, et al.
Publicado: (2021) -
An SMT-Based Approach for Verifying Binarized Neural Networks
por: Amir, Guy, et al.
Publicado: (2021) -
Training Neural Networks with Universal Adiabatic Quantum Computing
por: Abel, Steve, et al.
Publicado: (2023) -
Adiabatic superconducting cells for ultra-low-power artificial neural networks
por: Schegolev, Andrey E, et al.
Publicado: (2016) -
Neuromorphic Binarized Polariton Networks
por: Mirek, Rafał, et al.
Publicado: (2021)