From post

Adversarially trained neural representations are already as robust as biological neural representations.

, , , , , , и . ICML, том 162 из Proceedings of Machine Learning Research, стр. 8072-8081. PMLR, (2022)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed.

 

Другие публикации лиц с тем же именем

On the information bottleneck theory of deep learning, , , , , , и . Journal of Statistical Mechanics: Theory and Experiment, 2019 (12): 124020 (декабря 2019)Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception., , , , , , , и . NeurIPS, стр. 15595-15607. (2021)On the Information Bottleneck Theory of Deep Learning., , , , , , и . ICLR (Poster), OpenReview.net, (2018)Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness., , , , , , и . ICLR, OpenReview.net, (2023)Simulating a Primary Visual Cortex at the Front of CNNs Improves Robustness to Image Perturbations., , , , , и . NeurIPS, (2020)Adversarially trained neural representations are already as robust as biological neural representations., , , , , , и . ICML, том 162 из Proceedings of Machine Learning Research, стр. 8072-8081. PMLR, (2022)ProtoGraph: A Non-Expert Toolkit for Creating Animated Graphs., , , , и . IEEE VIS (Short Papers), стр. 176-180. IEEE, (2023)On the information bottleneck theory of deep learning, , , и . (2018)Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs., , , и . CoRR, (2021)Adversarially trained neural representations may already be as robust as corresponding biological neural representations., , , , , , и . CoRR, (2022)