all AI news
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming. (arXiv:2206.10816v1 [cs.LG])
June 23, 2022, 1:12 a.m. | Chuan Wen, Jianing Qian, Jierui Lin, Jiaye Teng, Dinesh Jayaraman, Yang Gao
cs.CV updates on arXiv.org arxiv.org
Across applications spanning supervised classification and sequential
control, deep learning has been reported to find "shortcut" solutions that fail
catastrophically under minor changes in the data distribution. In this paper,
we show empirically that DNNs can be coaxed to avoid poor shortcuts by
providing an additional "priming" feature computed from key input features,
usually a coarse output estimate. Priming relies on approximate domain
knowledge of these task-relevant key input features, which is often easy to
obtain in practical settings. For …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Data Engineer
@ Contact Government Services | Trenton, NJ
Data Engineer
@ Comply365 | Bristol, UK
Masterarbeit: Deep learning-basierte Fehler Detektion bei Montageaufgaben
@ Fraunhofer-Gesellschaft | Karlsruhe, DE, 76131
Assistant Manager ETL testing 1
@ KPMG India | Bengaluru, Karnataka, India