Cargando…
Dissociable Neural Representations of Adversarially Perturbed Images in Convolutional Neural Networks and the Human Brain
Despite the remarkable similarities between convolutional neural networks (CNN) and the human brain, CNNs still fall behind humans in many visual tasks, indicating that there still exist considerable differences between the two systems. Here, we leverage adversarial noise (AN) and adversarial interf...
Autores principales: | Zhang, Chi, Duan, Xiao-Han, Wang, Lin-Yuan, Li, Yong-Li, Yan, Bin, Hu, Guo-En, Zhang, Ru-Yuan, Tong, Li |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8375771/ https://www.ncbi.nlm.nih.gov/pubmed/34421567 http://dx.doi.org/10.3389/fninf.2021.677925 |
Ejemplares similares
-
A Systematic Approach for Explaining Time and Frequency Features Extracted by Convolutional Neural Networks From Raw Electroencephalography Data
por: Ellis, Charles A., et al.
Publicado: (2022) -
Brain-Computer Interface using neural network and temporal-spectral features
por: Wang, Gan, et al.
Publicado: (2022) -
Time-Frequency Representations of Brain Oscillations: Which One Is Better?
por: Bârzan, Harald, et al.
Publicado: (2022) -
BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python
por: Hazan, Hananel, et al.
Publicado: (2018) -
Single Image-Based Vignetting Correction for Improving the Consistency of Neural Activity Analysis in 2-Photon Functional Microscopy
por: Li, Dong, et al.
Publicado: (2022)