Machine Learning Design Patterns

by Valliappa Lakshmanan

Book Reviews

  • @VenetisPall The second book is a classic, but today I'd recommend more modern books. The Machine Learning Design Patterns book is very good, especially for those working in the industry. Machine Learning Bookcamp, from my friend @Al_Grigor is an excellent first book.Link to Tweet
  • @savov There is this...but these are design patterns. I'm looking to codify AI architectures. to Tweet

About Book

The design patterns in this book capture best practices and solutions to recurring problems in machine learning. Authors Valliappa Lakshmanan, Sara Robinson, and Michael Munn catalog the first tried-and-proven methods to help engineers tackle problems that frequently crop up during the ML process. These design patterns codify the experience of hundreds of experts into advice you can easily follow. The authors, three Google Cloud engineers, describe 30 patterns for data and problem representation, operationalization, repeatability, reproducibility, flexibility, explainability, and fairness. Each pattern includes a description of the problem, a variety of potential solutions, and recommendations for choosing the most appropriate remedy for your situation. You'll learn how to: Identify and mitigate common challenges when training, evaluating, and deploying ML models Represent data for different ML model types, including embeddings, feature crosses, and more Choose the right model type for specific problems Build a robust training loop that uses checkpoints, distribution strategy, and hyperparameter tuning Deploy scalable ML systems that you can retrain and update to reflect new data Interpret model predictions for stakeholders and ensure that models are treating users fairly