Cargando…
A pseudo-softmax function for hardware-based high speed image classification
In this work a novel architecture, named pseudo-softmax, to compute an approximated form of the softmax function is presented. This architecture can be fruitfully used in the last layer of Neural Networks and Convolutional Neural Networks for classification tasks, and in Reinforcement Learning hardw...
Autores principales: | Cardarilli, Gian Carlo, Di Nunzio, Luca, Fazzolari, Rocco, Giardino, Daniele, Nannarelli, Alberto, Re, Marco, Spanò, Sergio |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8319144/ https://www.ncbi.nlm.nih.gov/pubmed/34321514 http://dx.doi.org/10.1038/s41598-021-94691-7 |
Ejemplares similares
-
Author Correction: A pseudo-softmax function for hardware-based high speed image classification
por: Cardarilli, Gian Carlo, et al.
Publicado: (2021) -
Sensing and Detection of Traffic Signs Using CNNs: An Assessment on Their Performance
por: Canese, Lorenzo, et al.
Publicado: (2022) -
Deep Classification with Linearity-Enhanced Logits to Softmax Function
por: Shao, Hao, et al.
Publicado: (2023) -
EA(3): A softmax algorithm for evidence appraisal aggregation
por: De Pretis, Francesco, et al.
Publicado: (2021) -
Apple Disease Recognition Based on Convolutional Neural Networks With Modified Softmax
por: Li, Ping, et al.
Publicado: (2022)