Self-Training - Weak Supervision Using Untrained Neural Nets for MR Reconstruction - Beliz Gunel

Self-Training - Weak Supervision Using Untrained Neural Nets for MR Reconstruction - Beliz Gunel

Stanford MedAI via YouTube Direct link

Intro

1 of 13

1 of 13

Intro

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. 1 Intro
  2. 2 Inverse Problems in Imaging
  3. 3 ML Methods for MR Reconstruction
  4. 4 Key Observations & Current Challenges
  5. 5 Motivation Can we significantly reduce the large paired training dataset requirement for
  6. 6 Self-Training in Natural Language Processing
  7. 7 Self-Training for MRI Reconstruction
  8. 8 Untrained Neural Networks (Deep Image Prior)
  9. 9 Untrained Neural Networks (ConvDecoder)
  10. 10 Key Observations & Ongoing Work
  11. 11 We know how to simulate motion
  12. 12 Standardization of ML pipelines matter
  13. 13 Self-supervised learning methods trained in-domain can learn good image-level representations for MR images

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.