Description
This course consolidates everything you learned in the applied machine learning specialisation. You will now walk through an entire machine learning project in order to create a machine learning maintenance roadmap. You will comprehend and analyse how to deal with constantly changing data. You will also be able to recognise and interpret unintended consequences in your project. You will comprehend and define procedures for implementing and maintaining your applied machine learning model. By the end of this course, you will have all of the tools and knowledge necessary to confidently launch a machine learning project and prepare to optimise it in your business context.
To be successful, you should have at least a basic understanding of Python programming (e.g., be able to read and code trace existing code, be comfortable with conditionals, loops, variables, lists, dictionaries and arrays). You should be familiar with linear algebra (vector notation) and statistics (probability distributions and mean/median/mode).
Syllabus ;
1. Machine Learning Strategy
- Introduction to the course
- ML Readiness
- Risk Mitigation
- Experimental Mindset
- Build/Buy/Partner
- Setting up a Team
- Understanding and Communicating Change
- Weekly Summary
2. Responsible Machine Learning
- AI 4 Good & for all
- Positive Feedback Loops & Negative Feedback Loops
- Metric Design & Observing Behaviours
- Secondary Effects of Optimization
- Regulatory Concerns
- Weekly Summary
3. Machine Learning in Production & Planning
- Integrating Info Systems
- Users Break Things
- Time & Space complexity in production
- When do I retrain the model?
- Logging ML Model Versioning
- Knowledge Transfer
- Reporting Performance to Stakeholders4
- Weekly Summary
4. Care and Feeding of your Machine Learning System
- MLPL Recap
- Post Deployment Challenges
- QuAM Monitoring and Logging
- QuAM Testing
- QuAM Maintenance
- QuAM Updating
- Separating Datastack from Production
- Dashboard Essentials & Metrics Monitoring
- Weekly Summary