Understanding Robustness and Generalization of Artificial Neural Networks Through Fourier Masks
Despite the enormous success of artificial neural networks (ANNs) in many disciplines, the characterization of their computations and the origin of key properties such as generalization and robustness remain open questions. Recent literature suggests that robust networks with good generalization pro...
Main Authors: | Nikos Karantzas, Emma Besier, Josue Ortega Caro, Xaq Pitkow, Andreas S. Tolias, Ankit B. Patel, Fabio Anselmi |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-07-01
|
Series: | Frontiers in Artificial Intelligence |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2022.890016/full |
Similar Items
-
Robust deep learning object recognition models rely on low frequency information in natural images.
by: Zhe Li, et al.
Published: (2023-03-01) -
Revealing nonlinear neural decoding by analyzing choices
by: Qianli Yang, et al.
Published: (2021-11-01) -
Two-Argument Activation Functions Learn Soft XOR Operations Like Cortical Neurons
by: Juhyeon Kim, et al.
Published: (2022-01-01) -
A neural computation for visual acuity in the presence of eye movements.
by: Xaq Pitkow, et al.
Published: (2007-12-01) -
Editorial: Symmetry as a guiding principle in artificial and brain neural networks
by: Fabio Anselmi, et al.
Published: (2022-10-01)