J Feather, A Durango, R Gonzalez… - Advances in Neural …, 2019 - proceedings.neurips.cc
Deep neural networks have been embraced as models of sensory systems, instantiating representational transformations that appear to resemble those in the visual and auditory …
Discovering and exploiting shared, invariant neural activity in electroencephalogram (EEG) based classification tasks is of significant interest for generalizability of decoding models …
Y Dong, H Su, J Zhu, F Bao - arXiv preprint arXiv:1708.05493, 2017 - arxiv.org
Deep neural networks (DNNs) have demonstrated impressive performance on a wide array of tasks, but they are usually considered opaque since internal structure and learned …
Abstract Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school …
T Golan, PC Raju… - Proceedings of the …, 2020 - National Acad Sciences
Distinct scientific theories can make similar predictions. To adjudicate between theories, we must design experiments for which the theories make distinct predictions. Here we consider …
An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings …
Neural networks are vulnerable to input perturbations such as additive noise and adversarial attacks. In contrast, human perception is much more robust to such …
Deep neural networks are vulnerable to adversarial examples (AEs), which have adversarial transferability: AEs generated for the source model can mislead another (target) model's …
Today's computer vision models achieve human or near-human level performance across a wide variety of vision tasks. However, their architectures, data, and learning algorithms differ …