Cargando…
Multidimensional Face Representation in a Deep Convolutional Neural Network Reveals the Mechanism Underlying AI Racism
The increasingly popular application of AI runs the risk of amplifying social bias, such as classifying non-white faces as animals. Recent research has largely attributed this bias to the training data implemented. However, the underlying mechanism is poorly understood; therefore, strategies to rect...
Autores principales: | Tian, Jinhua, Xie, Hailun, Hu, Siyuan, Liu, Jia |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7987832/ https://www.ncbi.nlm.nih.gov/pubmed/33776675 http://dx.doi.org/10.3389/fncom.2021.620281 |
Ejemplares similares
-
The Face Inversion Effect in Deep Convolutional Neural Networks
por: Tian, Fang, et al.
Publicado: (2022) -
Implementation-Independent Representation for Deep Convolutional Neural Networks and Humans in Processing Faces
por: Song, Yiying, et al.
Publicado: (2021) -
Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image
por: Huan, Er-Yang, et al.
Publicado: (2017) -
Revealing the multidimensional mental representations of natural objects underlying human similarity judgments
por: Hebart, Martin N., et al.
Publicado: (2020) -
Modeling naturalistic face processing in humans with deep convolutional neural networks
por: Jiahui, Guo, et al.
Publicado: (2023)