Completed
33:28 AI generating biologically impossible annotations
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
AI in Biology - Distinguishing Hype from Reality
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00 Intro
- 2 1:26 How Valerie came across the enzyme prediction paper
- 3 14:07 Training data contamination
- 4 17:40 UniProt DB is essential... but has not enough funding
- 5 23:58 The importance of good data for ML algorithms
- 6 26:45 DeepVariant as a good application of AI in biology
- 7 30:07 Rachel's viral blog post
- 8 33:28 AI generating biologically impossible annotations
- 9 39:40 Can you use AI for labeling easy problems?
- 10 42:21 Lab in the loop
- 11 49:42 How understanding an E. coli enzyme function helped Valerie demystify human disease
- 12 56:51 The amount of energy needed to refute BS is an order of magnitude bigger than needed to produce it
- 13 1:02:33 Can AI cure all diseases within 10 years?
- 14 1:04:58 How hype can slow down progress
- 15 1:08:44 How do you separate hype from reality in a new paper
- 16 1:15:48 Is one PhD not enough?
