Completed
Welcome & Speaker Introduction Riva at Con 42 20 26
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
From Reliable Models to Resilient ML Platforms
Automatically move to the next video in the Classroom when playback concludes
- 1 Welcome & Speaker Introduction Riva at Con 42 20 26
- 2 Talk Overview: Moving ML from Lab to Production + Agenda
- 3 Why Production ML Is Hard: Drift, Scale, Latency & Availability
- 4 Modern Platforms vs Legacy: Cloud-Native Capabilities
- 5 IBM Cloud/SoftLayer as an Example Infrastructure Foundation
- 6 Pillars of Resilient ML Infrastructure: HA & Disaster Recovery
- 7 Security by Design: Zero Trust, DDoS/Ransomware Protection
- 8 Sustaining ML Workloads: Rate Limits, Traffic Spikes & DDoS Readiness
- 9 Segmentation, Environment Isolation & Secure Model Serving
- 10 Framework Alignment & Operational Controls: IAM, Audit Logs, Image Scanning
- 11 Performance Metrics & Resiliency Benchmarking SLOs/SLAs
- 12 People & Process: Cross-Functional Ownership for Production ML
- 13 Deployment Patterns: Cloud-Native vs Hybrid vs Multi-Cloud
- 14 Design Principles & Key Takeaways + Closing/Q&A
