Disaster-Proofing Machine Learning Pipelines.png

The machine learning (ML) pipeline involves a complex relationship between the data, the model, and its implementation—each with its own risks that can adversely affect the utility and profitability of the solution. This course is a primer on what these risks are, where they come from, and how to mitigate them effectively.

In this course, you’ll start with a comprehensive look at the data side of the pipeline, including data privacy, data drift, and more. You’ll learn how to mitigate these in theory and practice. You’ll also discover problems related to ML models such as bias, security, and adversarial attacks. Finally, you’ll learn some of the alternative AI paradigms that exist in the world today—from causal AI to federated learning to generative AI.

A deep understanding of where problems can arise is a critical part of a data engineer or data scientist’s ML knowledge. From a career perspective, this course’s content can effectively address the real risks faced by developers while setting up ML pipelines.

Mitigating Disasters in ML Pipelines

Which non-traditional ML type does _not_ make predictions but rather generates output not explicitly seen in the inputs?

Which non-traditional ML type does not make predictions but rather generates output not explicitly seen in the inputs?

They have the ability to handle high-frequency data.

They have better splitting logic and are therefore optimal in most cases.

What advantage do online random forests (ORFs) provide over regular random forests?

What advantage do online random forests (ORFs) provide over regular random forests?

Faster and computationally more efficient training and predictions

Lower risk of information interception by attackers

What is _not_ an advantage of federated learning?

What is not an advantage of federated learning?

The data required to build good causal AI algorithms is difficult to assemble and collect. 

The computational complexity of these algorithms is greater.

These models are black boxes and are less interpretable. 

Lurking variables are still a concern, and though there are methods to remove their effect, it can't be guaranteed.

**(Select all that apply.)** What are some disadvantages of causal AI methods? 

(Select all that apply.) What are some disadvantages of causal AI methods?

Alternatives to Traditional ML

Alternatives to Traditional ML

Test your knowledge of alternative ML solutions.

Introduction

Disasters in Data

Disasters in Models

Alternatives to Traditional ML

Conclusion

Assessment: Disasters in ML Pipelines

Quiz: Alternatives to Traditional ML