Cargando…
Deep Neural Networks with Multistate Activation Functions
We propose multistate activation functions (MSAFs) for deep neural networks (DNNs). These MSAFs are new kinds of activation functions which are capable of representing more than two states, including the N-order MSAFs and the symmetrical MSAF. DNNs with these MSAFs can be trained via conventional St...
Autores principales: | Cai, Chenghao, Xu, Yanyan, Ke, Dengfeng, Su, Kaile |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi Publishing Corporation
2015
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4581500/ https://www.ncbi.nlm.nih.gov/pubmed/26448739 http://dx.doi.org/10.1155/2015/721367 |
Ejemplares similares
-
Storage Capacities of Twin-Multistate Quaternion Hopfield Neural Networks
por: Kobayashi, Masaki
Publicado: (2018) -
Effects of bias current and control of multistability in 3D hopfield neural network
por: Boui A Boya, Bertrand Frederick, et al.
Publicado: (2023) -
Multistability in the epithelial-mesenchymal transition network
por: Xin, Ying, et al.
Publicado: (2020) -
Multistability in neural systems with random cross-connections
por: Breffle, Jordan, et al.
Publicado: (2023) -
The capacity for multistability in small gene regulatory networks
por: Siegal-Gaskins, Dan, et al.
Publicado: (2009)