#deeplearninig — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #deeplearninig, aggregated by home.social.
-
Interpolation Can Provably Preclude Invariance https://arxiv.org/abs/2211.15724
#Overfitting to the point of #interpolation can hinder invariance-inducing objectives: One cannot assume a #DeepLearninig model with an invariance penalty will indeed achieve any form of #invariance… suggests that “benign overfitting,” in which models generalize well despite interpolating, might not favorably extend to settings in which #robustness or #fairness are desirable. -
Interpolation Can Provably Preclude Invariance https://arxiv.org/abs/2211.15724
#Overfitting to the point of #interpolation can hinder invariance-inducing objectives: One cannot assume a #DeepLearninig model with an invariance penalty will indeed achieve any form of #invariance… suggests that “benign overfitting,” in which models generalize well despite interpolating, might not favorably extend to settings in which #robustness or #fairness are desirable. -
Interpolation Can Provably Preclude Invariance https://arxiv.org/abs/2211.15724
#Overfitting to the point of #interpolation can hinder invariance-inducing objectives: One cannot assume a #DeepLearninig model with an invariance penalty will indeed achieve any form of #invariance… suggests that “benign overfitting,” in which models generalize well despite interpolating, might not favorably extend to settings in which #robustness or #fairness are desirable. -
Interpolation Can Provably Preclude Invariance https://arxiv.org/abs/2211.15724
#Overfitting to the point of #interpolation can hinder invariance-inducing objectives: One cannot assume a #DeepLearninig model with an invariance penalty will indeed achieve any form of #invariance… suggests that “benign overfitting,” in which models generalize well despite interpolating, might not favorably extend to settings in which #robustness or #fairness are desirable. -
Interpolation Can Provably Preclude Invariance https://arxiv.org/abs/2211.15724
#Overfitting to the point of #interpolation can hinder invariance-inducing objectives: One cannot assume a #DeepLearninig model with an invariance penalty will indeed achieve any form of #invariance… suggests that “benign overfitting,” in which models generalize well despite interpolating, might not favorably extend to settings in which #robustness or #fairness are desirable. -
Hello 👋 I model human intelligence and underlying brain mechanisms using artificial neural networks. Focusing on vision and language. Incoming prof at EPFL, currently research scientist at MIT, looking to connect with people in #compneuro #neuroscience #NeuroAI #DeepLearninig #MachineLearming #vision #languageprocessing #NeuroscienceMigration #introduction