Cargando…
The Relationship between Sparseness and Energy Consumption of Neural Networks
About 50-80% of total energy is consumed by signaling in neural networks. A neural network consumes much energy if there are many active neurons in the network. If there are few active neurons in a neural network, the network consumes very little energy. The ratio of active neurons to all neurons of...
Autores principales: | Wang, Guanzheng, Wang, Rubin, Kong, Wanzeng, Zhang, Jianhai |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7710421/ https://www.ncbi.nlm.nih.gov/pubmed/33299397 http://dx.doi.org/10.1155/2020/8848901 |
Ejemplares similares
-
The Dynamic EEG Microstates in Mental Rotation
por: Kong, Wanzeng, et al.
Publicado: (2018) -
Neural Energy Supply-Consumption Properties Based on Hodgkin-Huxley Model
por: Wang, Yihong, et al.
Publicado: (2017) -
Multi-Granularity Analysis of Brain Networks Assembled With Intra-Frequency and Cross-Frequency Phase Coupling for Human EEG After Stroke
por: Ren, Bin, et al.
Publicado: (2022) -
Photoacoustic microscopy with sparse data by convolutional neural networks
por: Zhou, Jiasheng, et al.
Publicado: (2021) -
Dual-Branch Discrimination Network Using Multiple Sparse Priors for Image Deblurring
por: Li, Jialuo, et al.
Publicado: (2022)