This unit introduces how contemporary machine learning and data science diverge from traditional business intelligence, describing the shift from CRISP-DM to modern, multicomponent ML lifecycles. Students will examine the emergence of LLMs and foundation models, the role of off-the-shelf components, and core principles for production-ready, data-driven ML systems using a YouTube search agent as a running example.
Learning Objectives
- Analyze how data science practices diverge from business intelligence and articulate the implications for requirements, team roles, and system design in modern ML projects.
- Evaluate the evolution from CRISP-DM to modern, multicomponent ML lifecycles and identify the core components and data flows in a YouTube search agent architecture.
- Demonstrate understanding of large language models and foundation models by explaining their capabilities, limitations, and the trade-offs between off-the-shelf components and custom solutions.
- Apply principles of production-ready ML and a data-driven approach to construct a high-level plan that specifies data sources, system components, and evaluation metrics for a simple ML-backed search agent.
Curriculum
- 1 Section
- 9 Lessons
- 30 hours
Expand all sectionsCollapse all sections
- Unit 1 — Foundations of Modern ML Systems9
- 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