Deploying Machine Learning Solutions

Focused View

Janani Ravi

3:03:49

30 View

01 - Course Overview

01 - CourseTrailer DeployingMachineLearningSolutions.mp4

01:40

02 - Understanding Factors that Impact Deployed Models

02 - Module Overview.mp4

01:32

03 - Prerequisites and Course Outline.mp4

01:20

04 - The Classic Machine Learning Workflow.mp4

03:06

05 - New Realities of Deployed Models.mp4

06:43

06 - Overfitting.mp4

04:31

07 - Training-serving Skew.mp4

05:39

08 - Concept Drift.mp4

06:13

09 - Concerted Adversaries.mp4

02:16

10 - Deploying Machine Learning Models.mp4

02:34

11 - Module Summary.mp4

01:33

03 - Deploying Machine Learning Models to Flask

12 - Module Overview.mp4

01:08

13 - Serializing Model Parameters.mp4

03:32

14 - Demo - Serializing and Deserializing Models Using JSON.mp4

06:58

15 - Demo - Using Pickle and Joblib to Serialize and Deserialize Models.mp4

04:58

16 - Demo - Checkpointing Models and Resuming Training from a Checkpoint.mp4

06:13

17 - Demo - Serializing Pre-processors and Models.mp4

05:44

18 - Demo - Serializing Pipelines.mp4

02:04

19 - Using Flask for Model Deployment.mp4

02:22

20 - Demo - Deploying a Model for Prediction Using Flask.mp4

06:42

21 - Module Summary.mp4

01:12

04 - Deploying Machine Learning Models to Serverless Cloud Environments

22 - Module Overview.mp4

01:23

23 - Event-driven Serverless Compute.mp4

05:12

24 - Demo - Serializing Classification Models.mp4

03:40

25 - Demo - Uploading Pickle Files to Cloud Storage.mp4

04:38

26 - Demo - Deploying a Model to Google Cloud Functions.mp4

06:34

27 - Demo - Performing Predictions Using Cloud Functions.mp4

03:57

28 - Module Summary.mp4

01:15

05 - Deploying Machine Learning Models to Google AI Platform

29 - Module Overview.mp4

01:21

30 - Introducing the Google AI Platform.mp4

06:27

31 - Demo - Getting Started with Cloud AI Platform.mp4

02:28

32 - Demo - Creating a Model and a Version.mp4

04:53

33 - Demo - Scheduling an Evaluation Job to Sample Prediction Instances.mp4

05:14

34 - Demo - Testing the Deployed Model Using the Web Console.mp4

02:42

35 - Demo - Model Predictions Using the gcloud Command Line Utility.mp4

02:59

36 - Demo - Invoking the Predictions API Using cURL.mp4

04:26

37 - Demo - Monitoring Deployed Models Using Stackdriver.mp4

06:30

38 - Module Summary.mp4

01:25

06 - Deploying Deep Learning Models to AWS SageMaker

39 - Module Overview.mp4

01:23

40 - Introducing Amazon SageMaker.mp4

02:24

41 - Training a Model on SageMaker.mp4

02:40

42 - Deploying a Model on SageMaker.mp4

03:03

43 - Demo - Creating a SageMaker Notebook Instance.mp4

05:23

44 - Demo - Getting Started with SageMaker for Distributed Training.mp4

02:55

45 - Demo - Tensor Flow Script for Distributed Training.mp4

05:49

46 - Demo - Distributed Training Using the SageMaker Tensor Flow Estimator.mp4

06:01

47 - Demo - Deploying the Model for Predictions.mp4

05:22

48 - Demo - Auditing and Compliance Using Cloud Trail.mp4

04:06

49 - Summary and Further Study.mp4

01:39

Description

This course covers the important conceptual reasons why models underperform post-deployment, the actual implementation of model deployment using Python Flask, using serverless, cloud-based compute options and using platform-specific machine learning frameworks.

What You'll Learn?

Machine Learning is exploding in popularity, but serious early warning signs are emerging around the performance of ML models in production.

In this course, Deploying Machine Learning Solutions you will gain the ability to identify reasons why models might be under-performing in production after doing just fine in training and testing, and ways to mitigate this worrying phenomenon.

First, you will learn how training-serving skew, concept drift, and overfitting are different causes of model underperformance, and how they can be mitigated by post-deployment monitoring.

Next, you will discover how ML models can be deployed, that is made available on HTTP endpoints, using Flask, the popular Python web-serving framework. You will also see how you can deploy models to serverless environments such as Google Cloud Functions

Finally, you will work with platform-specific machine learning services such as Google AI Platform and Amazon SageMaker for model deployment.

When you’re finished with this course, you will have the skills and knowledge to identify issues with models that have been deployed but are not performing to expectations, as well as how to implement deployment using both on-prem and cloud infrastructure.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Machine Learning

Janani Ravi

Instructor's Courses

Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework. After spending years working in tech in the Bay Area, New York, and Singapore at companies such as Microsoft, Google, and Flipkart, Janani finally decided to combine her love for technology with her passion for teaching. She is now the co-founder of Loonycorn, a content studio focused on providing high-quality content for technical skill development. Loonycorn is working on developing an engine (patent filed) to automate animations for presentations and educational content.

Pluralsight

View courses Pluralsight

Pluralsight, LLC is an American privately held online education company that offers a variety of video training courses for software developers, IT administrators, and creative professionals through its website. Founded in 2004 by Aaron Skonnard, Keith Brown, Fritz Onion, and Bill Williams, the company has its headquarters in Farmington, Utah. As of July 2018, it uses more than 1,400 subject-matter experts as authors, and offers more than 7,000 courses in its catalog. Since first moving its courses online in 2007, the company has expanded, developing a full enterprise platform, and adding skills assessment modules.