This course is part of the Machine Learning Engineering for Production (MLOps) Specialization

4.6
stars
155 ratings

Laurence Moroney +1 more instructor

11,690 already enrolled

Offered By

Machine Learning Engineering for Production (MLOps) SpecializationDeepLearning.AI

About this Course

78,257 recent views

In the fourth course of Machine Learning Engineering for Production Specialization, you will learn how to deploy ML models and make them available to end-users. You will build scalable and reliable hardware infrastructure to deliver inference requests both in real-time and batch depending on the use case. You will also implement workflow automation and progressive delivery that complies with current MLOps practices to keep your production system running. Additionally,  you will continuously monitor your system to detect model decay, remediate performance drops, and avoid system failures so it can continuously operate at all times.  
Understanding machine learning and deep learning concepts is essential, but if you’re looking to build an effective AI career, you need production engineering capabilities as well. Machine learning engineering for production combines the foundational concepts of machine learning with the functional expertise of modern software development and engineering roles to help you develop production-ready skills.

Week 1: Model Serving Introduction
Week 2: Model Serving Patterns and Infrastructures
Week 3: Model Management and Delivery
Week 4: Model Monitoring and Logging

Flexible deadlines

Reset deadlines in accordance to your schedule.

Shareable Certificate

Earn a Certificate upon completion

100% online

Start instantly and learn at your own schedule.

Course 4 of 4 in the

Machine Learning Engineering for Production (MLOps) Specialization

Advanced Level

• Some knowledge of AI / deep learning

• Intermediate Python skills

• Experience with any deep learning framework (PyTorch, Keras, or TensorFlow)

Approx. 33 hours to complete

English

Subtitles: English, French

Skills you will gain

TensorFlow Serving
Model Monitoring
Model Registries
Machine Learning Operations (MLOps)
Generate Data Protection Regulation (GDPR)

Flexible deadlines

Reset deadlines in accordance to your schedule.

Shareable Certificate

Earn a Certificate upon completion

100% online

Start instantly and learn at your own schedule.

Course 4 of 4 in the

Machine Learning Engineering for Production (MLOps) Specialization

Advanced Level

• Some knowledge of AI / deep learning

• Intermediate Python skills

• Experience with any deep learning framework (PyTorch, Keras, or TensorFlow)

Approx. 33 hours to complete

English

Subtitles: English, French

Instructors

Instructor rating

4.55/5 (45 Ratings)

Laurence Moroney

Instructor

Lead AI Advocate, Google

366,719 Learners

15 Courses

Robert Crowe

Instructor

TensorFlow Developer Engineer, Google

24,638 Learners

3 Courses

Offered by

DeepLearning.AI

DeepLearning.AI is an education technology company that develops a global community of AI talent.

Syllabus - What you will learn from this course

Week

Week 1

5 hours to complete

Week 1: Model Serving: Introduction

Learn how to make your ML model available to end-users and optimize the inference process

5 hours to complete

7 videos (Total 34 min), 5 readings, 5 quizzes

7 videos

Course Overview4m

Introduction to Model Serving6m

Introduction to Model Serving Infrastructure5m

Deployment Options3m

Improving Prediction Latency and Reducing Resource Costs5m

Creating and deploying models to AI Prediction Platform2m

Installing TensorFlow Serving6m

5 readings

Ungraded Labs - Best Practices5m

Ungraded Lab - Introduction to Docker20m

Optional: Build, train, and deploy an XGBoost model on Cloud AI Platform45m

Ungraded Lab - Tensorflow Serving with Docker20m

Ungraded Lab - Serve a model with TensorFlow Serving30m

3 practice exercises

Introduction to Model Serving30m

Introduction to Model Serving Infrastructure30m

TensorFlow Serving30m

Week

Week 2

10 hours to complete

Week 2: Model Serving: Patterns and Infrastructure

Learn how to serve models and deliver batch and real-time inference results by building scalable and reliable infrastructure

10 hours to complete

8 videos (Total 44 min), 8 readings, 8 quizzes

8 videos

Model Serving Architecture4m

Model Servers: TensorFlow Serving3m

Model Servers: Other Providers5m

Scaling Infrastructure10m

Online Inference6m

Data Preprocessing4m

Batch Inference Scenarios5m

Batch Processing with ETL3m

8 readings

Documentation on model servers10m

Ungraded Lab - Deploy a ML model with FastAPI and Docker1h

Learn about scaling with boy bands10m

Explore Kubernetes and KubeFlow10m

Ungraded Lab: Intro to Kubernetes1h 10m

Ungraded Lab - Latency testing with Docker Compose and Locust45m

Data preprocessing10m

Ungraded Lab (Optional): Machine Learning with Apache Beam and TensorFlow45m

6 practice exercises

Model serving architecture30m

Scaling Infrastructure30m

Online Inference30m

Data Preprocessing30m

Batch inference scenarios30m

Batch Processing with ETL30m

Week

Week 3

12 hours to complete

Week 3: Model Management and Delivery

Learn how to implement ML processes, pipelines, and workflow automation that adhere to modern MLOps practices, which will allow you to manage and audit your projects during their entire lifecycle

12 hours to complete

9 videos (Total 82 min), 10 readings, 6 quizzes

9 videos

Experiment Tracking8m

Tools for Experiment Tracking7m

Introduction to MLOps11m

MLOps Level 0 5m

MLOps Levels 1&213m

Developing Components for an Orchestrated Workflow13m

Managing Model Versions7m

Continuous Delivery7m

Progressive Delivery7m

10 readings

Experiment Tracking10m

MLOps Resources10m

Ungraded Lab: Intro to Kubeflow Pipelines2h

Architecture for MLOps using TFX, Kubeflow Pipelines, and Cloud Build10m

Ungraded Lab: Developing TFX Custom Components45m

Ungraded Lab - Model Versioning with TF Serving40m

ML Model Management10m

Ungraded Lab - CI/CD pipelines with GitHub Actions1h

Continuous Delivery10m

Progressive Delivery10m

3 practice exercises

ML Experiments Management and Workflow Automation30m

MLOps Methodology30m

Model Management and Deployment Infrastructure30m

Week

Week 4

6 hours to complete

Week 4: Model Monitoring and Logging

Establish procedures to detect model decay and prevent reduced accuracy in a continuously operating production system

6 hours to complete

13 videos (Total 66 min), 7 readings, 5 quizzes

13 videos

Why Monitoring Matters6m

Observability in ML4m

Monitoring Targets in ML4m

Logging for ML Monitoring7m

Tracing for ML Systems3m

What is Model Decay?3m

Model Decay Detection2m

Ways to Mitigate Model Decay5m

Responsible AI5m

Legal Requirements for Secure and Private AI9m

Anonymization and Pseudonymisation 4m

Right to be Forgotten8m

Specialization recap and farewell1m

7 readings

Monitoring Machine Learning Models in Production10m

Addressing Model Decay10m

Responsible AI10m

GDPR and CCPA10m

Course 4 Optional References10m

Acknowledgements10m

Join our DeepLearning.AI Community!10m

3 practice exercises

Model Monitoring and Logging30m

Model Decay30m

GDPR and Privacy30m

Reviews

4.6

25 reviews

5 stars
71.16%
4 stars
22.08%
3 stars
3.06%
2 stars
2.45%
1 star
1.22%

TOP REVIEWS FROM DEPLOYING MACHINE LEARNING MODELS IN PRODUCTION

by VLMay 16, 2022

It's intense, applied, concrete and to the point. A very good course.

by AAApr 19, 2022

it's a pretty good overview, only downside is the focus on GCP

by WHSep 10, 2021

The most practical course for junior MLOPs engineers looking for the best productionization methodologie, and the tools that implement them.

by MNApr 21, 2022

This course is essential for data scientist if they want to embark on the journey of data scientist in industry. I learned a lot of useful techniques. Thank you team!

View all reviews

About the Machine Learning Engineering for Production (MLOps) Specialization

Understanding machine learning and deep learning concepts is essential, but if you’re looking to build an effective AI career, you need production engineering capabilities as well.

Effectively deploying machine learning models requires competencies more commonly found in technical fields such as software engineering and DevOps. Machine learning engineering for production combines the foundational concepts of machine learning with the functional expertise of modern software development and engineering roles. The Machine Learning Engineering for Production (MLOps) Specialization covers how to conceptualize, build, and maintain integrated systems that continuously operate in production. In striking contrast with standard machine learning modeling, production systems need to handle relentless evolving data. Moreover, the production system must run non-stop at the minimum cost while producing the maximum performance. In this Specialization, you will learn how to use well-established tools and methodologies for doing all of this effectively and efficiently. In this Specialization, you will become familiar with the capabilities, challenges, and consequences of machine learning engineering in production. By the end, you will be ready to employ your new production-ready skills to participate in the development of leading-edge AI technology to solve real-world problems.

Machine Learning Engineering for Production (MLOps)

Frequently Asked Questions

When will I have access to the lectures and assignments?
Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:
The course may not offer an audit option. You can try a Free Trial instead, or apply for Financial Aid.
The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
What will I get if I subscribe to this Specialization?
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.
Is financial aid available?
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

More questions? Visit the Learner Help Center.

Deploying Machine Learning Models in Production

About this Course

Skills you will gain