Completed
Key Observations & Current Challenges
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Self-Training - Weak Supervision Using Untrained Neural Nets for MR Reconstruction - Beliz Gunel
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Inverse Problems in Imaging
- 3 ML Methods for MR Reconstruction
- 4 Key Observations & Current Challenges
- 5 Motivation Can we significantly reduce the large paired training dataset requirement for
- 6 Self-Training in Natural Language Processing
- 7 Self-Training for MRI Reconstruction
- 8 Untrained Neural Networks (Deep Image Prior)
- 9 Untrained Neural Networks (ConvDecoder)
- 10 Key Observations & Ongoing Work
- 11 We know how to simulate motion
- 12 Standardization of ML pipelines matter
- 13 Self-supervised learning methods trained in-domain can learn good image-level representations for MR images
