Dendritic normalisation improves learning in sparsely connected artificial neural networks.
Artificial neural networks, taking inspiration from biological neurons, have become an invaluable tool for machine learning applications. Recent studies have developed techniques to effectively tune the connectivity of sparsely-connected artificial neural networks, which have the potential to be mor...
Guardado en:
Autores principales: | Alex D Bird, Peter Jedlicka, Hermann Cuntz |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Public Library of Science (PLoS)
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/a181e8475b0a4db9adbb0ef0f836a799 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science
por: Decebal Constantin Mocanu, et al.
Publicado: (2018) -
The morphological identity of insect dendrites.
por: Hermann Cuntz, et al.
Publicado: (2008) -
Sparse synaptic connectivity is required for decorrelation and pattern separation in feedforward networks
por: N. Alex Cayco-Gajic, et al.
Publicado: (2017) -
Artificial neural networks trained to detect viral and phage structural proteins.
por: Victor Seguritan, et al.
Publicado: (2012) -
Sparse-PE: A Performance-Efficient Processing Engine Core for Sparse Convolutional Neural Networks
por: Mahmood Azhar Qureshi, et al.
Publicado: (2021)