This unit introduces the shift from business intelligence to modern machine learning engineering, covering the evolution from CRISP-DM to multicomponent production systems and the impact of large language and foundation models. Students learn core principles, components (using a YouTube search agent case study), and the data-driven approach to prepare for designing and operating production ML systems in subsequent units.
Learning Objectives
- Analyze key differences between traditional business intelligence workflows and modern data science/ML workflows, including the limitations of CRISP-DM for multicomponent production systems
- Evaluate the roles, capabilities, and trade-offs of large language models, foundation models, and off-the-shelf components when integrated into production ML architectures
- Demonstrate understanding of the components and principles of a production ML system by mapping data pipelines, model training/deployment, and monitoring processes for a YouTube search agent case study
- Design a concise, data-driven plan for a simple production ML pipeline that specifies data collection, validation, iteration practices, and appropriate technology choices for each phase
Curriculum
- 1 Section
- 9 Lessons
- 30 hours
Expand all sectionsCollapse all sections
- Unit 1 — Foundations of Production Machine Learning9
- 1.1Data Science Is Diverging from Business Intelligence20 mins
- 1.2From CRISP-DM to Modern, Multicomponent ML Systems20 mins
- 1.3The Emergence of LLMs Has Increased ML’s Power and Complexity20 mins
- 1.4What You Can Expect from This Book20 mins
- 1.5Components of a YouTube Search Agent20 mins
- 1.6Principles of a Production Machine Learning System20 mins
- 1.7The Emergence of Foundation Models20 mins
- 1.8The Role of Off-the-Shelf Components20 mins
- 1.9The Data-Driven Approach20 mins
Instructor
Free
Leave a Reply