Cargando…
Deep physical neural networks trained with backpropagation
Deep-learning models have become pervasive tools in science and engineering. However, their energy requirements now increasingly limit their scalability(1). Deep-learning accelerators(2–9) aim to perform deep learning energy-efficiently, usually targeting the inference phase and often by exploiting...
Autores principales: | Wright, Logan G., Onodera, Tatsuhiro, Stein, Martin M., Wang, Tianyu, Schachter, Darren T., Hu, Zoey, McMahon, Peter L. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8791835/ https://www.ncbi.nlm.nih.gov/pubmed/35082422 http://dx.doi.org/10.1038/s41586-021-04223-6 |
Ejemplares similares
-
Training Deep Spiking Neural Networks Using Backpropagation
por: Lee, Jun Haeng, et al.
Publicado: (2016) -
Enabling Spike-Based Backpropagation for Training Deep Neural Network Architectures
por: Lee, Chankyu, et al.
Publicado: (2020) -
Fractional-Order Deep Backpropagation Neural Network
por: Bao, Chunhui, et al.
Publicado: (2018) -
Backpropagation with biologically plausible spatiotemporal adjustment for training deep spiking neural networks
por: Shen, Guobin, et al.
Publicado: (2022) -
An optical neural network using less than 1 photon per multiplication
por: Wang, Tianyu, et al.
Publicado: (2022)