Exploring fMRI RDMs: enhancing model robustness through neurobiological data
Artificial neural networks (ANNs) are sensitive to perturbations and adversarial attacks. One hypothesized solution to adversarial robustness is to align manifolds in the embedded space of neural networks with biologically grounded manifolds. Recent state-of-the-art works that emphasize learning rob...
Main Authors: | William Pickard, Kelsey Sikes, Huma Jamil, Nicholas Chaffee, Nathaniel Blanchard, Michael Kirby, Chris Peterson |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-12-01
|
Series: | Frontiers in Computer Science |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fcomp.2023.1275026/full |
Similar Items
-
Mapping the emotional homunculus with fMRI
by: Michelle Giraud, et al.
Published: (2024-06-01) -
Leveraging linear mapping for model-agnostic adversarial defense
by: Huma Jamil, et al.
Published: (2023-10-01) -
Demystifying visual word form area visual and nonvisual response properties with precision fMRI
by: Jin Li, et al.
Published: (2024-12-01) -
Processing of zero-derived words in English: An fMRI investigation
by: Pliatsikas, C, et al.
Published: (2014) -
An fMRI protocol for administering liquid incentives to human participants
by: Debbie M. Yee, et al.
Published: (2022-12-01)