机构名称：
¥ 1.0
Invited Talks Microsoft Research, Attributing model behavior at scale 2023 TrustML Young Scientist Seminar, Datamodels: predicting predictions from training data 2023 Stanford MedAI Seminar, Datamodels: predicting predictions from training data 2022 Google Brain, Datamodels: predicting predictions from training data 2022 SIAM Mathematics of Data Science, Datamodels: predicting predictions from training data 2022 OpenAI, Datamodels：预测训练数据2022 Samsung AI中心的预测，对2020 MIT视觉研讨会的深度学习现象的经验分析，确定数据集复制2020年伯克利CHAI中的偏见，仔细研究了深度政策梯度算法2020 Microsoft研究，Microsoft研究Microsoft Research，如何批量正常化？2019 Simons Institute，对抗性示例不是错误，它们是功能2019年两个Sigma，更仔细地查看深度政策梯度算法2019两个Sigma，强大的对抗性示例2018 Intel Labs，3D对抗性示例2018
Andrew IlyasAndrew Ilyas
主要关键词
相关文件推荐
