Dive into a comprehensive lecture on setting up Machine Learning projects like a professional. Learn about the ML lifecycle, assess project feasibility and impact, explore project archetypes, and develop a keen focus on metrics and baselines. Gain insights into why ML projects fail and how to avoid common pitfalls. Follow a running case study throughout the lecture to apply concepts in real-world scenarios. Explore key topics including project prioritization, choosing appropriate metrics for optimization, and establishing effective baselines to evaluate model performance. Access an extensive summary document for further study and reference.
ML Projects - Full Stack Deep Learning - Spring 2021
Overview
Syllabus
- Introduction
- Why Do ML Projects Fail?
- Lecture Overview and Running Case Study
- Lifecycle Thinking about the activities in an ML project
- Prioritizing Projects Assessing the feasibility and impact of the projects
- Archetypes Knowing the main categories of projects and implications for project management
- Metrics Picking a single number to optimize
- Baselines Figuring out if your model is performing well
- Conclusion
Taught by
The Full Stack
