Generalization error, model bias, and model variance

Let's not forget the goal is to train models that generalize to new data. How can we formalize this and use estimates to determine what steps to take to improve performance?

Covers:
0:00 Generalization Error
2:21 Derivation for squared error
4:19 Definitions model bias and variation
6:19 Underfitting and overfitting
8:10 Reducing model bias and variance
9:15 Holdout sets
12:33 Comparing model metrics

Please let me know about any improvements or corrections that can be made to the video.
Any opinions are solely my own.

Sources:
https://en.wikipedia.org/wiki/Bias%E2...
https://en.wikipedia.org/wiki/Overfit...
https://en.wikipedia.org/wiki/General...
  / the-bias-variance-tradeoff  
https://www.analyticsvidhya.com/blog/...
   • Bias/Variance (C2W1L02)   (would definitely recommend these videos as well)

Music:
Swans In Flight - Asher Fulero (youtube music library, no attribution required)
---
Summer Evening by Keys of Moon |   / keysofmoon  
Music promoted by https://www.chosic.com/free-music/all/
Attribution 4.0 International (CC BY 4.0)
https://creativecommons.org/licenses/...
---
We Are the Rain - Aakash Gandhi (youtube music library, no attribution required)
---
The Beauty of Maths by Meydän | https://linktr.ee/meydan
Music promoted by https://www.chosic.com/free-music/all/
Creative Commons CC BY 4.0
https://creativecommons.org/licenses/...
---
Art of silence by uniq
  / uniqofficial  
Attribution 4.0 International (CC BY 4.0)
https://creativecommons.org/licenses/...
Music promoted by https://www.chosic.com/free-music/all/
---
Faultlines - Asher Fulero (youtube music library, no attribution required)