Deeplearning - Ai Deeplearning - Ai
Deeplearning - Ai Deeplearning - Ai
DeepLearning.AI makes these slides available for educational purposes. You may not use or distribute
these slides for commercial purposes. You may make copies of these slides and use or distribute them for
educational purposes as long as you cite DeepLearning.AI as the source of the slides.
Andrew Ng
Evaluate multiple ideas in parallel
Ideas for cat detection:
• Fix pictures of dogs being recognized as cats
• Fix great cats (lions, panthers, etc..) being misrecognized
• Improve performance on blurry images
Image
1
2
3
..
.
% of total
Andrew Ng
Error Analysis
Cleaning up
deeplearning.ai Incorrectly labeled
data
Incorrectly labeled examples
y 1 0 1 1 0 1 1
Andrew Ng
Error analysis
Incorrectly
Image Dog Great Cat Blurry Comments
labeled
…
Labeler missed cat
98 in background
99
Drawing of a cat;
100 Not a real cat.
Goal of dev set is to help you select between two classifiers A & B.
Andrew Ng
Correcting incorrect dev/test set examples
Andrew Ng
Speech recognition example
Training Dev/test
Voice keyboard
Andrew Ng
Mismatched training
and dev/test data
Training error
Dev error
Andrew Ng
More general formulation
Andrew Ng
Mismatched training
and dev/test data
Addressing data
deeplearning.ai
mismatch
Addressing data mismatch
• Carry out manual error analysis to try to understand difference
between training and dev/test sets
Andrew Ng
Artificial data synthesis
+ =
Andrew Ng
Artificial data synthesis
Car recognition:
Andrew Ng
Learning from
multiple tasks
Transfer learning
deeplearning.ai
Transfer learning
x !"
x !"
Andrew Ng
When transfer learning makes sense
Andrew Ng
Learning from
multiple tasks
Multi-task
deeplearning.ai
learning
Simplified autonomous driving example
Andrew Ng
Neural network architecture
x !"
Andrew Ng
When multi-task learning makes sense
• Training on a set of tasks that could benefit from having
shared lower-level features.
• Usually: Amount of data you have for each task is quite
similar.
Andrew Ng
End-to-end deep
learning
What is
deeplearning.ai end-to-end
deep learning
What is end-to-end learning?
Speech recognition example
Andrew Ng
Face recognition
Andrew Ng
More examples
Machine translation
Andrew Ng
End-to-end deep
learning
Whether to use
deeplearning.ai
end-to-end learning
Pros and cons of end-to-end deep learning
Pros:
• Let the data speak
• Less hand-designing of components needed
Cons:
• May need large amount of data
• Excludes potentially useful hand-designed
components
Andrew Ng
Applying end-to-end deep learning
Key question: Do you have sufficient data to learn
a function of the complexity needed to map x to y?
Andrew Ng