Course 3: Structuring Machine Learning Projects Week 2 Notes

[mbhushan]

Applying end to end deep learning:

Pros and Cons of end to end deep learning.

End to End Deep Learning:

When multitask make sense:

Multitask Learning:

Transfer Learning:

Data Mismatch:

Bias and Variance on mismatched training/dev/test set data

Bias and Variance with mismatched data

Training and Testing on different distributions

Error Analysis: incorrect labelled data:

Error Analysis: Evaluate multiple ideas in parallel