Completed
MLOps Architecture for Scale: Containers, Versioning, Monitoring
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
ML-Powered IoT - From Warehouse Data to Production Intelligence in Real Time
Automatically move to the next video in the Classroom when playback concludes
- 1 Welcome & Elevator Pitch: ML + IoT for Real-Time Production Intelligence
- 2 Meet the Speaker: Digital Supply Chain IT at Honeywell
- 3 The Real Problem: Tons of Warehouse Data, Little Actionable Insight
- 4 Why Traditional ML Fails in Production Data, Integration, Performance
- 5 Deep Dive: Data Quality Issues—Sensor Failures, Drift, Interference
- 6 Integration Headaches: APIs, Latency, and Sync Problems
- 7 From Raw IoT Data to ML Features: Rolling Windows, Events, Anomalies
- 8 Handling Messy/Missing Data: Imputation, Sensor Fusion, Metadata
- 9 MLOps Architecture for Scale: Containers, Versioning, Monitoring
- 10 Safer Go-Live: Shadow Mode, Canary Releases, A/B Tests, Rollouts
- 11 Model Drift Reality: Detection, Retraining, and Staying Current
- 12 Edge vs Cloud vs Hybrid ML: Latency vs Accuracy Tradeoffs
- 13 High-Value Use Cases: Predictive Maintenance, Forecasting, Smart Picking
- 14 Responsible AI in Operations: Fairness, Explainability, Validation
- 15 Trends Reshaping Warehouses: AutoML, 5G, Green/Lean Computing
- 16 Lessons from the Field: What Makes Production ML Projects Win
- 17 From Insights to Implementation: Practical Next Steps & Closing
