Explore how to ensure reliability in ML models. Gain insights into software testing, ML-specific techniques, runtime checks, and monitoring tools to build robust ML systems effectively.

MyAwesomeDocker.tar.gz

MyAwesomeDocker

TorchJob

spa_run

spa_run_python

mypy_example

Ensuring the reliability and robustness of machine learning models is essential to building successful ML-powered applications.

This course begins with a thorough introduction to software testing essentials, particularly use cases within the machine learning context. You’ll learn about topics related to software testing, including unit and integration testing and more advanced testing techniques. Next, you’ll learn the best practices in software testing and dive into ML-specific testing techniques, such as behavioral and smoke tests. Lastly, you’ll cover the aspects of ML software reliability outside of testing, including runtime checks and type hinting.

By the end of this course, you'll be equipped with the knowledge and skills to ensure the reliability and robustness of your machine learning systems. You’ll be able to apply software engineering principles to your ML processes, create and execute efficient testing approaches, and utilize monitoring tools to identify and resolve problems in your ML systems.

Reliable Machine Learning

## Regression tests with exact values

Engineers build an ML pipeline with many things encapsulated deeply under the hood. This leads to a significant chance of unexpected deviation after minor or unrelated changes from first sight.

For example, we may update the `pandas` version to get some new functionality, which leads to implicitly updating `numpy`. Therefore, the result of some ML training pipelines will diverge a bit because of the introduced optimization, let's say in `np.linalg`.

To be informed about such a situation, we can prepare a regression test checking the exact value of some pipelines. Let’s look at the test below:



# Regression tests with exact values

Engineers build an ML pipeline with many things encapsulated deeply under the hood. This leads to a significant chance of unexpected deviation after minor or unrelated changes from first sight.

For example, we may update the `pandas` version to get some new functionality, which leads to implicitly updating `numpy`. Therefore, the result of some ML training pipelines will diverge a bit because of the introduced optimization, let's say in `np.linalg`.

To be informed about such a situation, we can prepare a regression test checking the exact value of some pipelines. Let’s look at the test below:



Check if the model consistently produces the same result between multiple test runs.

Introduction to Reliable ML

Software Testing

Best and Worst Practices

ML-Specific Tests

ML Software Reliability outside of Tests

Wrapping Up

Appendix

Tests for Exact Values

Regression tests with exact values