Cargando…
Counterfactual Explanation of Brain Activity Classifiers Using Image-To-Image Transfer by Generative Adversarial Network
Deep neural networks (DNNs) can accurately decode task-related information from brain activations. However, because of the non-linearity of DNNs, it is generally difficult to explain how and why they assign certain behavioral tasks to given brain activations, either correctly or incorrectly. One of...
Autores principales: | Matsui, Teppei, Taki, Masato, Pham, Trung Quang, Chikazoe, Junichi, Jimura, Koji |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8966478/ https://www.ncbi.nlm.nih.gov/pubmed/35369003 http://dx.doi.org/10.3389/fninf.2021.802938 |
Ejemplares similares
-
Evaluation of the Hierarchical Correspondence between the Human Brain and Artificial Neural Networks: A Review
por: Pham, Trung Quang, et al.
Publicado: (2023) -
GANterfactual—Counterfactual Explanations for Medical Non-experts Using Generative Adversarial Learning
por: Mertes, Silvan, et al.
Publicado: (2022) -
Model agnostic generation of counterfactual explanations for molecules
por: Wellawatte, Geemi P., et al.
Publicado: (2022) -
PreCoF: counterfactual explanations for fairness
por: Goethals, Sofie, et al.
Publicado: (2023) -
Adversarial counterfactual augmentation: application in Alzheimer’s disease classification
por: Xia, Tian, et al.
Publicado: (2022)