Completed
Intro
Class Central Classrooms beta
YouTube playlists curated by Class Central.
Classroom Contents
How Can You Trust Machine Learning?
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Math Myth of ML (circa 2008)
- 3 spaces between the Math
- 4 trust for whom?
- 5 Train a neural network to predict wolf v. husky
- 6 Explanations for neural network prediction
- 7 Accuracy vs Interpretability
- 8 Explaining predictions
- 9 Explaining prediction of Inception Neural Network
- 10 Anchors for Visual Question Answering
- 11 Type 1 Diabetes Management
- 12 Standard Intervention
- 13 Oversensitivity in image classification
- 14 Beyond Test-Set Accuracy
- 15 Closing the Loop with Simple Data Augmentation
- 16 Checklist: Test Linguistic Capabilities of Model
- 17 Checklist: Categories of Tests
- 18 Addressing Challenge of Test Creation
- 19 User Study: Quora Question Pairs (n=18, 2 hours)
- 20 Minding the Gap
- 21 Adaptive Loss Alignment (ALA)
- 22 And this gap is increasing with foundation models...
- 23 Optimizing for multiple metrics
