0% completed

All LessonsFree Lessons (3)

Introduction

Introduction The Standard ML Pipeline Sources of Disasters Quiz: ML Pipeline and Sources of Disasters

Disasters in Data

Introduction to Data Bias Diagnosing Data Bias Theory of Data Bias Mitigation Practice of Data Bias Mitigation Case Study: COMPAS in US Justice System Data Drift Detecting Data Drift Data Privacy Reidentification Example Theory of Ensuring Data Privacy Ensuring Data Privacy in Practice Quiz: Disasters in Data

Disasters in Models

Understanding Model Bias Large Language Models Post-Training Model Bias Mitigation In-Training Model Bias Mitigation Adversarial Attacks Thwarting Adversarial Attacks Other Model Attacks Intro to Model Explainability Explainability Methods Adversarial Attacks on Explanations Case Study: Chest X-rays Quiz: Disasters in Models

Project

Measuring Causal Relations with Python

Alternatives to Traditional ML

Federated Learning Causal AI Online Learning Neurosymbolic AI Generative AI Quiz: Alternatives to Traditional ML

Project

Adversarial Robustness of Neural Networks

Conclusion

Course Assessment

Assessment: Disasters in ML Pipelines

Mitigating Disasters in ML Pipelines/

...

/

Final Thoughts

Final Thoughts

Final thoughts on this course.

We'll cover the following...

Concluding thoughts
What's next?
Feedback

Concluding thoughts

Congratulations on completing Disaster-Proofing Machine Learning Pipelines!

Hopefully it is clear from this course that the machine learning lifecycle does not stop at ...