Deflecting Adversarial Attacks
Qin, Yao, Frosst, Nicholas, Raffel, Colin, Cottrell, Garrison, Hinton, Geoffrey
Year of Publication 18.02.2020
Year of Publication 18.02.2020
Get full text
Journal Article
Mitigating harm in language models with conditional-likelihood filtration
Ngo, Helen, Raterink, Cooper, Araújo, João G. M, Zhang, Ivan, Chen, Carol, Morisot, Adrien, Frosst, Nicholas
Year of Publication 04.08.2021
Year of Publication 04.08.2021
Get full text
Journal Article
System and Method for Training Language Models Using Already Trained Language Models
GHANAVI, Rozhina, CREMER, Christopher Alexander, FROSST, Nicholas Myles Wisener
Year of Publication 08.06.2023
Get full text
Year of Publication 08.06.2023
Patent
SYSTEM AND METHOD FOR TRAINING LANGUAGE MODELS USING ALREADY TRAINED LANGUAGE MODELS
CREMER, CHRISTOPHER ALEXANDER, FROSST, NICHOLAS MYLES WISENER, GHANAVI, ROZHINA
Year of Publication 03.06.2023
Get full text
Year of Publication 03.06.2023
Patent
Neural Additive Models: Interpretable Machine Learning with Neural Nets
Agarwal, Rishabh, Melnick, Levi, Frosst, Nicholas, Zhang, Xuezhou, Lengerich, Ben, Caruana, Rich, Hinton, Geoffrey
Year of Publication 28.04.2020
Year of Publication 28.04.2020
Get full text
Journal Article
Neural network training using the soft nearest neighbor loss
Frosst, Nicholas Myles Wisener, Hinton, Geoffrey E, Papernot, Nicolas Guy Robert
Year of Publication 26.03.2024
Get full text
Year of Publication 26.03.2024
Patent
CAPSULE NEURAL NETWORKS
HINTON, Geoffrey E, FROSST, Nicholas Myles Wisener, AGHDAM, Sara Sabour Rouh
Year of Publication 09.08.2023
Get full text
Year of Publication 09.08.2023
Patent
Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions
Qin, Yao, Frosst, Nicholas, Sabour, Sara, Raffel, Colin, Cottrell, Garrison, Hinton, Geoffrey
Year of Publication 05.07.2019
Year of Publication 05.07.2019
Get full text
Journal Article