Author
Released
8/17/2018- Defining scalability
- Tools and techniques for scalable machine learning
- Architecture design patterns for scalable systems
- Machine learning models as services
- Containerizing models
- Kubernetes for container orchestration
- Monitoring performance
- Best practices for scaling machine learning models
Skill Level Intermediate
Duration
Views
- [Instructor] Welcome to this course on scaling machine learning models. In this course, you'll learn about the difference between developing machine learning models and deploying them to a scalable production environment. We'll start by reviewing the model-building process, and discuss the requirements for ensuring that our applications are scalable. We will then examine three layers of a scalable machine learning stack. First is using services to expose machine learning models through APIs. Second, we'll look at containers for deploying models and related code to the production environment.
And then we'll conclude with a look at orchestration tools for managing clusters of servers running our machine learning models. And we'll also discuss the need for monitoring in a production environment. So let's get started on scaling machine learning models.
Related Courses
-
DevOps Foundations: Containers
with David Linthicum1h 16m Beginner -
Spark for Machine Learning & AI
with Dan Sullivan1h 51m Beginner -
DevOps for Data Scientists
with Dan Sullivan32m 16s Intermediate -
Learning Kubernetes
with Karthik Gaekwad2h 25m Beginner
-
Introduction
-
1. The Need to Scale ML Models
-
2. Design Patterns for Scalable ML Applications
-
Running models as services2m 15s
-
APIs for ML model services4m 38s
-
3. Deploying ML Models as Services
-
4. Running ML Services in Containers
-
Introduction to Docker3m 28s
-
Example Docker build process3m 36s
-
5. Scaling ML Services with Kubernetes
-
Running services in clusters3m 20s
-
Introduction to Kubernetes3m 45s
-
-
6. ML Services in Production
-
Service performance data2m 21s
-
Docker container monitoring1m 29s
-
Kubernetes monitoring1m 36s
-
Conclusion
-
Next steps1m 17s
- Mark as unwatched
- Mark all as unwatched
Are you sure you want to mark all the videos in this course as unwatched?
This will not affect your course history, your reports, or your certificates of completion for this course.
CancelTake notes with your new membership!
Type in the entry box, then click Enter to save your note.
1:30Press on any video thumbnail to jump immediately to the timecode shown.
Notes are saved with you account but can also be exported as plain text, MS Word, PDF, Google Doc, or Evernote.
Share this video
Embed this video
Video: Scaling ML models