I know Machine Learning but... am I ready for the real world?
summary
A presenter with backend and SRE experience explains how the real challenge is not building ML models but deploying, integrating, monitoring and observing them in production. The talk covers options for serving ML models in production, how they integrate models into existing products, deployment workflows and practical monitoring/observability techniques that let teams deploy and monitor models in minutes.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 8:16What is ML?
- 14:19ML challenges
- 22:31ML platform evolution
- 34:31Lessons learned
- 39:44Q&A
related talks
52mThe ML Lifecycle in Combat Conditions
06mMachine learning is about your data and deployment
44mSRE and ML: Why It Matters
29mDeploying ML Models and the Things That Go Wrong
39mAn SRE Approach to Monitoring ML in Production
30mChallenges of machine learning: The new ML lifecycle
30mThe State of Production Machine Learning in 2023
54mML Beyond Metrics: Challenges of Using ML Systems in the Real World