AWS Machine Learning: A Complete Guide With Python
4.4 (143 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
2,549 students enrolled
Wishlisted Wishlist

Please confirm that you want to add AWS Machine Learning: A Complete Guide With Python to your Wishlist.

Add to Wishlist

AWS Machine Learning: A Complete Guide With Python

Learn about cloud based machine learning algorithms and how to integrate with your applications
4.4 (143 ratings)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
2,549 students enrolled
Created by Chandra Lingam
Last updated 6/2017
Current price: $10 Original price: $200 Discount: 95% off
5 hours left at this price!
30-Day Money-Back Guarantee
  • 9 hours on-demand video
  • 2 Articles
  • 3 Supplemental Resources
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
What Will I Learn?
  • Learn AWS Machine Learning algorithms, Predictive Quality assessment, Model Optimization
  • Integrate predictive models with your application using simple and secure APIs
  • Convert your ideas into highly scalable products in days
View Curriculum
  • All materials and software instructions are covered in housekeeping lecture
  • Familiarity with a programming language
  • AWS Account – if you want to try the hands-on activities. AWS charges a small amount for model creation and predictions
  • Some basic knowledge of Pandas, Numpy, Matplotlib would be helpful but not absolutely needed

*** NEW PREVIEW VIDEOS: Take a look at several newly enabled Preview videos. All lectures in Section 3 and Section 4 on Linear Regression are available for preview as well as Section 15 Integration objectives 

Note: AWS Machine Learning is not part of free-tier.  So, you will incur a small charge when creating and running prediction on models. For this course, I spent USD 5-6 total for creating and testing all models. ***

This course is designed to make you an expert in AWS Machine Learning and it teaches you how to convert your cool ideas into highly scalable products in a matter of days.

Biggest challenge for a Data Science professional is how to convert the proof-of-concept models into actual products that your customers can use. There are several courses on machine learning that teach you how to build models in R, Python, Matlab and so forth.  However, converting a model into a scalable solution and integrating with your existing application requires a lot of effort and development.  The real success of your ideas and concepts depends on how soon you can put the capabilities in the hands of your customers.

With AWS Machine Learning service, you can easily conduct experiments and test your concepts. Once you are happy, you can instantly scale to support millions of requests. No separate development work needed.

This course is focused on three aspects:

The Core of the machine learning process is the algorithm itself.  Gaining an intuitive understanding of the algorithm, how does it find the solution, and what are the knobs to tweak is essential for a successful career in this field.  That is where we will focus first.

Once we build the model, how do we know if it is good or bad? Or If we want to compare two different models, how do we decide which one to pick?  We will look at industry standard metrics and powerful visualization tools that AWS provides to assess the goodness of a model.

The third aspect and most exciting part of model development is putting the prediction capability in the hands of the users, validate how they are using it and identify what needs to be refined.  There is a whole section in this course dedicated to integration of machine learning models with your application.  We will walk thru several integration and security options.

This course is completely hands-on with examples using: AWS Web Console, Python Notebook Files, and Web clients built on AngularJS. You will also learn and integrate security into exercises using variety of AWS provided capabilities including Cognito.

There are Quizzes and supporting resources as well.

Who is the target audience?
  • This course is designed for anyone who is interested in machine learning and data science
  • If you are new to machine learning, this is a perfect course to upskill yourself and fastest way to learn machine learning
  • If you are an experienced practitioner, you will gain insight into AWS Machine Learning capability and learn how you can convert your ideas into highly scalable solution in a matter of days
  • AWS Certification - If you are preparing for certification, you will learn best practices and gain hands-on experience on securely deploying products using AWS Cloud
Students Who Viewed This Course Also Viewed
Curriculum For This Course
108 Lectures
Introduction and Housekeeping
9 Lectures 48:17

Introduction to AWS Machine Learning Course, Topics Covered, Course Structure

Preview 04:12

Python and Boto3 Install Tips

  1. Setup Anaconda Python Development Environment
  2. Install Boto3 Module needed for AWS
Python Development Environment and Boto3 Setup

1. Setup Course Folder in local machine

2. Download Project Source Code

3. Download Data files

Project Source Code and Data Setup

Introduction to Python Development Environment, Pandas, NumPy, Matplotlib

Preview 13:24

Setup your AWS Root Account 

Lab: AWS Root Account Setup

Configure Identity and Access Management Security. Add lower privilege IAM user accounts that will be used for hands-on machine learning exercises.

Lab: AWS Security Setup

  1. Setup Simple Storage Service (S3) Bucket and Security Policies to allow access to machine learning
  2. S3 is the storage location where training, evaluation and test file will be kept
Lab: AWS S3 Bucket Setup and Configure Security

Summary of Introduction, Development Environment Setup and AWS Configuration


Introduction and House Keeping Quiz
5 questions
AWS Learning Algorithms, Terminology, Data Types, Data Visualization
6 Lectures 27:15

Learn about standard machine learning terminologies that we will be using in this course

Machine Learning Terminology

Introduces data types supported by AWS Machine Learning with examples

Preview 02:55

Introduces linear regression models with examples; hands-on python data analysis for assessing the input features.

Linear Regression Introduction

Introduces binary classification models with examples; hands-on python data analysis for assessing the input features.

Binary Classification Introduction

Introduces multiclass classification models with examples; hands-on python data analysis for assessing the input features.

Multiclass Classification Introduction

Overview of plotting capability in python using Matplotlib and how various functions appear in a graph.  Useful for understanding relation between input and output attributes.

Data Visualization - Linear, Log, Quadratic and More

Algorithm and Terminology Quiz
10 questions
Linear Regression
3 Lectures 22:54

Understand concepts behind linear regression.  How does the algorithm predict a numeric value, what optimization steps does it go through, how does it evaluate cost/loss and more

Preview 15:46

Understand how linear regression is able to fit non-linear shapes

Preview 05:09

Linear Regression Quiz
5 questions
AWS - Linear Regression Models
8 Lectures 50:50

Create Training Data and Characteristics of input features and target attribute

Preview 06:35

How to create datasource in AWS, how to review statistics, missing values, invalid values, schema definition

Preview 12:20

How to create a new model in AWS with default configuration recipe

Preview 04:17

AWS Models Quiz
7 questions

  1. How to evaluate regression model predictive quality
  2. RMSE Metrics
  3. Residual Histograms
Preview 04:51

Review RMSE, Residual Histograms for the model we trained in AWS

Preview 10:52

Review the configuration or recipe used for training the model

Preview 02:27

Learn how to customize the recipe or configuration for training a model

Preview 07:05

Review the results of default recipe versus custom recipe models

Summarize the learnings

Preview 02:23

AWS Regression Metrics Quiz
7 questions
Adding Features To Improve Model
4 Lectures 31:53

Prepare training data with quadratic features

Lab: Quadratic Fit Training Data

  1. Evaluate a model that attempts to fit a complex shape with a straight line
  2. Identify underfit issue from metrics and visualization
Lab: Underfitting With Linear Features

  1. Add additional quadratic features and train model
  2. Review model performance with metrics and visualization
Lab: Normal Fit With Quadratic Features

  1. Learn how to fit more complex shapes
  2. Learn how to review metrics and detect underfitting
  3. Understand how adding relevant features improves model performance
4 Lectures 24:13

How would a model respond to a condition where there are lot more features than necessary?

What would happen if magnitude of features are very different?  

Let's find out!

Lab: Impact of Features With Different Magnitude

How to fix a condition where features with large magnitude dominate the outcome?

Normalization to the rescue!

Concept: Normalization to smoothen magnitude differences

Let's rebuild the model with normalization enabled through recipes.

How is the model predictive quality now?

Lab: Train Model With Feature Normalizaton

Having lot of features and higher order generally help improve the model quality.  However, when the magnitudes are very different, consider normalizing the numeric features


Underfitting and Normalization Quiz
4 questions
Adding Complex Features
7 Lectures 20:05

Prepare a training data target features having a complex shape

Lab: Prepare Training Data

Learn how to add complex features to your training data

Lab: Adding Complex Features

Train model with variety of input feature scenarios

Lab: Train Model With Higher Order Features

Assess model performance that fits complex shape with degree 1 features

Lab: Performance Of Model With Degree 1 Features

Assess model performance that fits complex shape with degree 4 features

Lab: Performance of Model with Degree 4 Features

Assess model performance that fits complex shape with degree 15 features

Lab: Performance of Model With Degree 15 Features

Summary of performance findings and how higher order features enable fitting complex shape

Kaggle Bike Hourly Rental Prediction
4 Lectures 25:30

Review Problem, Initial Data Assessment, Features, Data Type and Model Strategy

Review Kaggle Bike Train Problem And Dataset

Train Model

Lab: Train Model To Predict Hourly Rental

Assess Prediction Quality, Performance Summary and Next Steps

Lab: Evaluate Prediction Quality

Linear Regression Summary and Concepts we have covered so far

Linear Regression Wrapup and Summary
Logistic Regression
8 Lectures 43:43

Learn about classification problem, solution objectives, model representation, probability score and cut-off

Binary Classification - Logistic Regression, Loss Function, Optimization

Simple example that shows how logistic regression process works

Lab: Binary Classification Approach

How to evaluate performance of a classification algorithm.  Terminology introduction

True Positive, True Negative, False Positive and False Negative

Discuss objectives of the optimization algorithm

Lab: Logistic Optimization Objectives

Logistic cost function characteristics

Lab: Logistic Cost Function

Exercise to understand how differences between actual and predicted value affect cost

Lab: Cost Example

How does algorithm march towards optimal solution

Optimizing Weights

Summary of logistic regression process, logistic function, cost function, optimization algorithm and terminologies


Logistic Regression Quiz
5 questions
Onset of Diabetes Prediction
11 Lectures 54:13

Discuss problem, solution objective, input features, target attribute and assessment of data

Problem Objective, Input Data and Strategy

Prepare Training, Evaluation and Test Datasets

Lab: Prepare For Training

Training a Classification model on AWS

Lab: Training a Classification Model

Metrics to evaluate predictive quality of a classification algorithm. True Positive Rate, False Positive Rate, Accuracy, Precision and more 

Concept: Classification Metrics

Visual Insight into predictive quality of model using powerful Positive and Negative Histograms provided by AWS

Concept: Classification Insights with AWS Histograms

Area Under Curve Metrics for summarizing prediction quality

Concept: AUC Metric

Assess quality of Diabetes prediction model using AUC, Positive Negative Histograms and other metrics

Lab: Review Diabetes Model Performance

  1. Visual insight into how modifying cut-off threshold changes the prediction quality metrics
  2. Discussion on why adjusting cut-off is good strategy depending on problem domain
Lab: Cutoff Threshold Interactive Testing

Use new dataset and assess model performance using AWS Model Evaluation capability

Lab: Evaluating Prediction Quality With Additional Dataset

  1. Batch Prediction Example
  2. Code walk-through to Compute classification quality metrics in Python
Lab: Batch Prediction and Compute Metrics

Summary of Binary Classifiers, Training Models and Predictive Quality Metrics


Logistic Regression Metrics Quiz
4 questions
7 More Sections
About the Instructor
Chandra Lingam
4.4 Average rating
1,139 Reviews
19,442 Students
6 Courses
Data Scientist and Solutions Architect

Chandra Lingam spent 15 years at Intel, developing and managing systems that handled hundreds of terabytes of worldwide factory data.  

Chandra is an expert on Amazon Web Services, mission critical systems and machine learning.  He has a rich background in systems development in both traditional IT data center and Cloud based infrastructure. For those new to AWS, he is uniquely positioned to guide you to become an expert in AWS Cloud Platform.

He has a Master's degree in Computer Science from ASU and Bachelor's degree in Computer Science from Thiagarajar College of Engineering, Madurai