HDSI Seminar Series | Spurious or Causal? Studying Failure Modes of Deep Learning and Ways to Fix Them with Soheil Feizi from mathematics for deep learning Watch Video
Preview(s):
Gallery
Play Video: (Note: The default playback of the video is HD VERSION. If your browser is buffering the video slowly, please play the REGULAR MP4 VERSION or Open The Video below for better experience. Thank you!)
⏲ Duration: 36 min 49 sec ✓ Published: 16-Nov-2021
Description: Over the last decade, deep models have enjoyed wide empirical success. However, innpractice, these models are not reliable due to their sensitivity against adversarial ornnatural input distributional shifts as well as a lack of meaningful reasoning behind theirnpredictions. In this talk, I will show that a root cause of these issues is the heavynreliance of deep models on non-causal and spurious features in their inferences. I willnthen explain our progress in understanding failure modes of deep
Play Video: (Note: The default playback of the video is HD VERSION. If your browser is buffering the video slowly, please play the REGULAR MP4 VERSION or Open The Video below for better experience. Thank you!)