4.51 out of 5
4.51
251 reviews on Udemy

Deployment of Machine Learning Models

Build Machine Learning Model APIs
Instructor:
Soledad Galli
2,124 students enrolled
English [Auto-generated]
Deploy machine learning models into the cloud
Build machine learning model APIs
Send and receive requests from deployed machine learning models
Design testable, version controlled and reproducible production code for model deployment
Build reproducible machine learning pipelines
Understand the optimal machine learning architecture
Create continuous and automated integrations to deploy your models
Understand the different resources available to you to productionise your models

Learn how to put your machine learning models into production.

What is model deployment?

Deployment of Machine learning models, or simply, putting models into production, means making your models available to your other business systems. By deploying models, other systems can send data to them and get their predictions, which are in turn populated back into the company systems. Through machine learning model deployment, you and your business can begin to take full advantage of the model you built.

When we think about data science, we think about how to build machine learning models. We think about which algorithm will be more predictive, how to engineer our features and which variables to use to make the models more accurate. However, how we are going to actually use those models is often neglected. And yet this is the most important step in the machine learning pipeline. Only when a model is fully integrated with the business systems, we can extract real value from its predictions.

Why take this course?

This is the first and only online course where you can learn how to deploy machine learning models. In this course, you will learn every aspect of how to put your models in production. The course is both comprehensive, and yet easy to follow. Throughout this course you will learn all the steps and infrastructure required to deploy machine learning models professionally.

In this course, you will have at your fingertips, the sequence of steps that you need to follow to deploy a machine learning model, plus a project template with full code, that you can adapt to deploy your own models.

What is the course structure?

The course begins from the most common starting point for the majority of data scientists: a jupyter notebook with a machine learning model trained in it. The course will take you through all the necessary steps and infrastructure required to take that model into the cloud, where it can be called from the other systems in the business.

The lectures include an explanation of the systems and architecture required to put models into production, followed by presentations on best coding practices for building reproducible pipelines and testable, versioned, error free production code. The lectures include videos that cover the different scripts required for model deployment.

Who are the instructors?

We have gathered a fantastic team to teach this course. Sole is a leading data scientist in finance and insurance, with 3+ years of experience in building and implementing machine learning models in the field, and multiple IT awards and nominations. Chris is an AI software engineer with enormous experience in building APIs and deploying machine learning models, allowing business to extract full benefit from their implementation and decisions.

Who is this course for?

This course is suitable for data scientists looking to deploy their first machine learning model, and software developers looking to transition into AI software engineering. Deployment of machine learning models is a very advanced topic in the data science path so the course will also be suitable for intermediate and advanced data scientists.

To sum up:

With more than 50 lectures and 8 hours of video this comprehensive course covers every aspect of model deployment. Throughout the course you will use python as your main language and other open source technologies that will allow you to host and make calls to your machine learning models.

Introduction

1
Introduction to the course
2
Course curriculum overview
3
Knowledge requirements
4
How to Approach this course
5
Guide to Setting up your Computer
6
Slides covered in this course
7
Notes covered in this course
8
FAQ: Where can I learn more about the required skills?

Machine Learning Pipeline - Research Environment

1
Machine Learning Pipeline: Overview
2
Machine Learning Pipeline: Feature Engineering
3
Machine Learning Pipeline: Feature Selection
4
Machine Learning Pipeline: Model Building
5
Jupyter notebooks covered in this section
6
Data Analysis - Demo
7
Feature Engineering - Demo
8
Feature Selection - Demo
9
Model Building - Demo
10
Getting Ready for Deployment - Demo
11
Bonus: Machine Learning Pipeline: Additional Resources
12
Randomness in Machine Learning - Setting the Seed
13
Randomness in Machine Learning - Additional reading resources
14
FAQ: Where can I learn more about the pipeline steps?

Machine Learning System Architecture

1
Machine Learning System Architecture and Why it Matters
2
Specific Challenges of Machine Learning Systems
3
Machine Learning System Approaches
4
Machine Learning System Component Breakdown
5
Building a Reproducible Machine Learning Pipeline
6
Additional Reading Resources

Building a Reproducible Machine Learning Pipeline

1
Production Code: overview
2
Procedural Programming Pipeline
3
Designing a Custom Pipeline
4
Leveraging a Third Party Pipeline: Scikit-Learn
5
Third Party Pipeline: Create Scikit-Learn compatible Feature Transformers
6
Third Party Pipeline: Closing Remarks
7
Scikit-Learn Pipeline - Code
8
Bonus: Should feature selection be part of the pipeline?
9
Bonus: Additional Resources on Scikit-Learn
10
Bonus: Resources to Improve as a Python Developer

Course Setup and Key Tools

1
Section 5.1 - Introduction
2
Section 5.2 - Installing and Configuring Git
3
Section 5.3 - How to Use the Course Resources, Monorepos + Git Refresher
4
Section5.3b - Opening Pull Requests
5
Section5.3c - Primer on Monorepos
6
Section 5.4a - Operating System Differences and Gotchas
7
Section 5.4b - System Path and Pythonpath Demo
8
Section 5.5a - Quick Word for More Advanced Students
9
Section5.5b - Virtualenv Introduction
10
Section5.5c - Requirements files Introduction
11
Section5.5d - Virtualenv refresher
12
Section 5.6 - Text Editors / IDEs
13
Section 5.7 - Engineering and Python Best Practices
14
Section 5.8 - Wrap Up

Creating a Machine Learning Pipeline Application

1
6.1 - Introduction
2
6.2 - Training the Model
3
6.3 - Connecting the Pipeline
4
6.4a - Gotchas
5
6.4 - Making Predictions with the Model
6
6.5 - Data Validation in the Model Package
7
6.6 - Feature Engineering in the Pipeline
8
6.7 - Versioning and Logging
9
6.8 - Building the Package
10
6.9 - Wrap Up

Serving the model via REST API

1
7.1 - Introduction
2
7.2 - Creating the API Skeleton
3
7.2b - Flask Crash Course
4
7.3 - Adding Config and Logging
5
7.4 - Adding the Prediction Endpoint
6
7.5 - Adding a Version Endpoint
7
7.6 - API Schema Validation
8
7.7 - Wrap Up

Continuous Integration and Deployment Pipelines

1
8.1 - Introduction to CI/CD
2
8.2 - Setting up CircleCI
3
8.3 - Setup Circle CI Config
4
8.4 - Publishing the Model to Gemfury
5
8.5 - Testing the CI Pipeline
6
8.6 - Wrap Up

Differential Testing

1
9.1 - Introduction
2
9.2 - Setting up Differential Tests
3
9.3 - Differential Tests in CI (Part 1 of 2)
4
9.4 - Differential Tests in CI (Part 2 of 2)
5
9.5 Wrap Up

Deploying to a PaaS (Heroku) without Containers

1
10.1 - Introduction
2
10.2 - Heroku Account Creation
3
10.3 - Heroku Config
4
10.4 - Testing the Deployment Manually
5
10.5 - Deploying to Heroku via CI
6
10.6 - Wrap Up

Running Apps with Containers (Docker)

1
11.1 Introduction to Containers and Docker
2
11.2 Installing Docker
You can view and review the lecture materials indefinitely, like an on-demand channel.
Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
4.5
4.5 out of 5
251 Ratings

Detailed Rating

Stars 5
146
Stars 4
81
Stars 3
25
Stars 2
2
Stars 1
1
ac37e985f236d15473f4ed76c522d94e
30-Day Money-Back Guarantee

Includes

8 hours on-demand video
18 articles
Full lifetime access
Access on mobile and TV
Certificate of Completion