Cargando…
Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers †
Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the Minimum Description Length (MDL) principle. Treating the ne...
Autor principal: | Lin, Baihan |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8774926/ https://www.ncbi.nlm.nih.gov/pubmed/35052085 http://dx.doi.org/10.3390/e24010059 |
Ejemplares similares
-
Progressively Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
por: Lee, Hong-Yu, et al.
Publicado: (2023) -
Unsupervised cross-domain translation via deep learning and adversarial attention neural networks and application to music-inspired protein designs
por: Buehler, Markus J.
Publicado: (2023) -
Regularization for Unsupervised Learning of Optical Flow
por: Long, Libo, et al.
Publicado: (2023) -
Edge detection networks inspired by neural mechanisms of selective attention in biological visual cortex
por: Zhang, Zhenguang, et al.
Publicado: (2022) -
Editorial: Neuroscience-inspired visual sensing and understanding
por: Wu, Qingbo, et al.
Publicado: (2023)