Cargando…
Utilizing Information Bottleneck to Evaluate the Capability of Deep Neural Networks for Image Classification †
Inspired by the pioneering work of the information bottleneck (IB) principle for Deep Neural Networks’ (DNNs) analysis, we thoroughly study the relationship among the model accuracy, [Formula: see text] and [Formula: see text] , where [Formula: see text] and [Formula: see text] are the mutual inform...
Autores principales: | Cheng, Hao, Lian, Dongze, Gao, Shenghua, Geng, Yanlin |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7514945/ https://www.ncbi.nlm.nih.gov/pubmed/33267170 http://dx.doi.org/10.3390/e21050456 |
Ejemplares similares
-
On the Difference between the Information Bottleneck and the Deep Information Bottleneck
por: Wieczorek, Aleksander, et al.
Publicado: (2020) -
Markov Information Bottleneck to Improve Information Flow in Stochastic Neural Networks
por: Tang Nguyen, Thanh, et al.
Publicado: (2019) -
Variational Information Bottleneck for Semi-Supervised Classification
por: Voloshynovskiy, Slava, et al.
Publicado: (2020) -
Information Bottleneck Classification in Extremely Distributed Systems
por: Ullmann, Denis, et al.
Publicado: (2020) -
Image-Based Ship Detection Using Deep Variational Information Bottleneck
por: Ngo, Duc-Dat, et al.
Publicado: (2023)