Cargando…
PresB-Net: parametric binarized neural network with learnable activations and shuffled grouped convolution
In this study, we present a novel performance-enhancing binarized neural network model called PresB-Net: Parametric Binarized Neural Network. A binarized neural network (BNN) model can achieve fast output computation with low hardware costs by using binarized weights and features. However, performan...
Autores principales: | Shin, Jungwoo, Kim, HyunJin |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8771783/ https://www.ncbi.nlm.nih.gov/pubmed/35111925 http://dx.doi.org/10.7717/peerj-cs.842 |
Ejemplares similares
-
A storage-efficient ensemble classification using filter sharing on binarized convolutional neural networks
por: Kim, HyunJin, et al.
Publicado: (2022) -
LEMABE: a novel framework to improve analogy-based software cost estimation using learnable evolution model
por: Dashti, Maedeh, et al.
Publicado: (2022) -
Introspective analysis of convolutional neural networks for improving discrimination performance and feature visualisation
por: Shafiq, Shakeel, et al.
Publicado: (2021) -
Multilabel convolution neural network for facial expression recognition and ordinal intensity estimation
por: Ekundayo, Olufisayo, et al.
Publicado: (2021) -
An intelligent approach for Arabic handwritten letter recognition using convolutional neural network
por: Ullah, Zahid, et al.
Publicado: (2022)