ML Strategy (1)-Introduction to ML Strategy
Why ML Strategy
()
Orthogonalization
()
ML Strategy (1)-Connect with your Mentors and Fellow Learners on Discourse!
Connect with your Mentors and Fellow Learners on Discourse!
ML Strategy (1)-Setting Up your Goal
Single Number Evaluation Metric
()
Satisficing and Optimizing Metric
()
Train/Dev/Test Distributions
()
Size of the Dev and Test Sets
()
When to Change Dev/Test Sets and Metrics?
()
ML Strategy (1)-Comparing to Human-level Performance
Why Human-level Performance?
()
Avoidable Bias
()
Understanding Human-level Performance
()
Surpassing Human-level Performance
()
Improving your Model Performance
()
ML Strategy (1)-Lecture Notes (Optional)
Lectures in PDF
ML Strategy (1)-Machine Learning Flight Simulator
Machine Learning Flight Simulator
ML Strategy (1)-Heroes of Deep Learning (Optional)
Andrej Karpathy Interview
()
ML Strategy (2)-Error Analysis
Carrying Out Error Analysis
()
Cleaning Up Incorrectly Labeled Data
()
Build your First System Quickly, then Iterate
()
ML Strategy (2)-Mismatched Training and Dev/Test Set
Training and Testing on Different Distributions
()
Bias and Variance with Mismatched Data Distributions
()
Addressing Data Mismatch
()
ML Strategy (2)-Learning from Multiple Tasks
Transfer Learning
()
Multi-task Learning
()
ML Strategy (2)-End-to-end Deep Learning
What is End-to-end Deep Learning?
()
Whether to use End-to-end Deep Learning
()
ML Strategy (2)-Lecture Notes (Optional)
Lectures in PDF
ML Strategy (2)-Heroes of Deep Learning (Optional)
Ruslan Salakhutdinov Interview
()
ML Strategy (2)-Acknowledgments
Acknowledgments