4.3 out of 5
4.3
763 reviews on Udemy

2019 AWS SageMaker and Machine Learning – With Python

Learn about cloud based machine learning algorithms and how to integrate with your applications
Instructor:
Chandra Lingam
7,314 students enrolled
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

*** UPDATE MAY-2019.  1. Model endpoint integration with hands-on-labs for (Direct Client, Microservice, API Gateway).  2. Hyperparameter Tuning – Learn how to automatically tune hyperparameters ***

*** UPDATE MARCH-12-2019.  I came to know that new accounts are not able to use AWSML Service.  AWS is asking new users to use SageMaker Service. 

I have restructured the course to start with SageMaker Lectures First.  Machine Learning Service Lectures are still available in the later parts of the course.  Newly updated sections start with 2019 prefix.

All source code for SageMaker Course is now available on Github

The new house keeping lectures cover all the steps for setting up code from GitHub.

***

*** SageMaker Lectures –  DeepAR – Time Series Forecasting, XGBoost – Gradient Boosted Tree algorithm in-depth with hands-on.  XGBoost has won several competitions and is a very popular Regression and Classification Algorithm, Factorization Machine based Recommender Systems and PCA for dimensionality reduction ***

There are several courses on Machine Learning and AI.  What is special about this course?

 

Here are the top reasons:

 

  1. Cloud based machine learning keeps you focused on the current best practices.  

  2. In this course, you will Learn most useful algorithms. Don’t waste your time sifting through mountains of techniques that are in the wild

  3. Cloud based service is very easy to integrate with your application and has support for wide variety of programming languages.

  4. Whether you have small data or big data, elastic nature of the AWS cloud allows you to handle them all.

  5. There is also No upfront cost or commitment – Pay only for what you need and use

In this course, you will learn AI and Machine Learning in three different ways:

AWS Machine Learning

AWS Machine Learning Service is designed for complete beginners. 

 

You will learn three popular easy to understand linear algorithms from the ground-up

 

You will gain hands-on knowledge on complete lifecycle – from model development, measuring quality, tuning, and integration with your application

AWS SageMaker

The next service is AWS SageMaker.

 

If you are comfortable coding in Python, SageMaker service is for you.

 

You will learn how to deploy your own Jupyter Notebook instance on the AWS Cloud.

 

You will gain hands-on model development experience on very powerful and popular machine learning algorithms like

 

  • XGBoost – a gradient boosted tree algorithm that has won several competitions,

     

  • Recurrent Neural Networks for Time Series forecasting,

     

  • Factorization Machines for high dimensional sparse datasets like Click Stream data

     

  • Neural Network based Image Classifiers,

     

  • Dimensionality reduction with Principal Component Analysis

     

  • and much more

Application Services

In Application Services section of this course,

 

You will learn about a set of pre-trained services that you can directly integrate with your application.

 

You will gain hands-on experience in ready-to-use Vision service for image and video analysis, Conversation chatbots and Language Services for text translation, Speech recognition, and text to speech and more

I am looking forward to seeing you in the course.

Introduction and Housekeeping

1
Introduction

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

2
Root Account Setup and Billing Dashboard Overview
3
Enable Access to Billing Data for IAM Users
4
Create Users Required For the Course
5
AWS Command Line Interface Tool Setup and Summary
6
Six Advantages of Cloud Computing
7
AWS Global Infrastructure Overview

2019 SageMaker Housekeeping

1
Downloadable Resources

Following Downloadable Resources are available in this lecture:

1. Source Code and Data Setup Document

2. Introduction to Machine Learning and Concepts Document

2
Demo - S3 Bucket Setup
3
Demo - Setup SageMaker Notebook Instance
4
2019 Demo - Source Code and Data Setup

2019 Machine Learning Concepts

1
2019 Introduction to Machine Learning, Concepts, Terminologies
2
2019 Data Types - How to handle mixed data types
3
2019 Introduction to Python Notebook Environment
4
2019 Introduction to working with Missing Data
5
2019 Data Visualization - Linear, Log, Quadratic and More

2019 SageMaker Service Overview

1
Downloadable Resources
2
SageMaker Overview
3
Compute Instance Families and Pricing
4
Algorithms and Data Formats Supported For Training and Inference

XGBoost - Gradient Boosted Trees

1
Introduction to XGBoost

"XGBoost (eXtreme Gradient Boosting) is a popular and efficient open-source implementation of the gradient boosted trees algorithm. Gradient boosting is a supervised learning algorithm that attempts to accurately predict a target variable by combining the estimates of a set of simpler, weaker models. XGBoost has done remarkably well in machine learning competitions because it robustly handles a variety of data types, relationships, and distributions, and the large number of hyperparameters that can be tweaked and tuned for improved fits. This flexibility makes XGBoost a solid choice for problems in regression, classification (binary and multiclass), and ranking"

https://docs.aws.amazon.com/sagemaker/latest/dg/xgboost.html

2
Source Code Overview

For Source Code Setup from GitHub, please refer :

2019 Demo - Source Code and Data Setup in SageMaker Housekeeping Section

3
Demo - Create Files in SageMaker Data Formats and Save Files To S3
4
Demo - Working with XGBoost - Linear Regression Straight Line Fit
5
Demo - XGBoost Example with Quadratic Fit
6
Demo - Kaggle Bike Rental Data Setup, Exploration and Preparation
7
Demo - Kaggle Bike Rental Model Version 1
8
Demo - Kaggle Bike Rental Model Version 2
9
Demo - Kaggle Bike Rental Model Version 3
10
Demo - Training on SageMaker Cloud - Kaggle Bike Rental Model Version 3
11
Demo - Invoking SageMaker Model Endpoints For Real Time Predictions
12
Demo - Invoking SageMaker Model Endpoints From Client Outside of AWS
13
How to remove SageMaker endpoints and Shutdown Notebook Instance
14
Creating EndPoint From Existing Model Artifacts
15
XGBoost Hyper Parameter Tuning
16
Demo - XGBoost Multi-Class Classification Iris Data
17
Demo - XGBoost Binary Classifier For Diabetes Prediction
18
Demo - XGBoost Binary Classifier for Edible Mushroom Prediction
19
Summary - XGBoost

SageMaker - Principal Component Analysis (PCA)

1
Downloadable Resources
2
Introduction to Principal Component Analysis (PCA)

"PCA is an unsupervised machine learning algorithm that attempts to reduce the dimensionality (number of features) within a dataset while still retaining as much information as possible. This is done by finding a new set of features called components, which are composites of the original features that are uncorrelated with one another. They are also constrained so that the first component accounts for the largest possible variability in the data, the second component the second most variability, and so on."

https://docs.aws.amazon.com/sagemaker/latest/dg/pca.html

3
PCA Demo Overview
4
Demo - PCA with Random Dataset
5
Demo - PCA with Correlated Dataset
6
Cleanup Resources on SageMaker
7
Demo - PCA with Kaggle Bike Sharing - Overview and Normalization
8
Demo - PCA Local Model with Kaggle Bike Train
9
Demo - PCA training with SageMaker
10
Demo - PCA Projection with SageMaker
11
Exercise : Kaggle Bike Train and PCA
12
Summary

SageMaker - Factorization Machines

1
Downloadable Resources
2
Introduction to Factorization Machines

"A factorization machine is a general-purpose supervised learning algorithm that you can use for both classification and regression tasks. It is an extension of a linear model that is designed to capture interactions between features within high dimensional sparse datasets economically. For example, in a click prediction system, the factorization machine model can capture click rate patterns observed when ads from a certain ad-category are placed on pages from a certain page-category. Factorization machines are a good choice for tasks dealing with high dimensional sparse datasets, such as click prediction and item recommendation."

https://docs.aws.amazon.com/sagemaker/latest/dg/fact-machines.html

3
MovieLens Dataset
4
Demo - Movie Recommender Data Preparation
5
Demo - Movie Recommender Model Training
6
Demo - Movie Predictions By User

SageMaker - DeepAR Time Series Forecasting

1
Downloadable Resources
2
Introduction to DeepAR Time Series Forecasting

"The Amazon SageMaker DeepAR forecasting algorithm is a supervised learning algorithm for forecasting scalar (one-dimensional) time series using recurrent neural networks (RNN)"

https://docs.aws.amazon.com/sagemaker/latest/dg/deepar.html

3
DeepAR Training and Inference Formats
4
Working with Time Series Data, Handling Missing Values
5
Demo - Bike Rental as Time Series Forecasting Problem
6
Demo - Bike Rental Model Training
7
Demo - Bike Rental Prediction
8
Demo - DeepAR Categories
9
Demo - DeepAR Dynamic Features Data Preparation
10
Demo - DeepAR Dynamic Features Training and Prediction
11
Summary

2019 Integration Options - Model Endpoint

1
Downloadable Resources
2
Integration Overview
3
Install Python and Boto3 - Local Machine
4
Install SageMaker SDK, GIT Client, Source Code, Security Permissions
5
Client to Endpoint using SageMaker SDK
6
Client to Endpoint using Boto3 SDK
7
Microservice - Lambda to Endpoint - Payload
8
Microservice - Lambda to Endpoint
9
Microservice - API Gateway, Lambda to Endpoint

2019 SageMaker HyperParameter Tuning

1
Downloadable Resources
2
Introduction to Hyperparameter Tuning

"Amazon SageMaker automatic model tuning, also known as hyperparameter tuning, finds the best version of a model by running many training jobs on your dataset using the algorithm and ranges of hyperparameters that you specify. It then chooses the hyperparameter values that result in a model that performs the best, as measured by a metric that you choose."

https://docs.aws.amazon.com/sagemaker/latest/dg/automatic-model-tuning.html

3
Lab: Tuning Movie Rating Factorization Machine Recommender System
4
Lab: Step 2 Tuning Movie Rating Recommender System

AWS Machine Learning Service

1
2019 MARCH - Important Update: AWS Machine Learning Service Deprecated
2
Python Development Environment and Boto3 Setup
  1. Setup Anaconda Python Development Environment
  2. Install Boto3 Module needed for AWS
3
Project Source Code and Data Setup

1. Setup Course Folder in local machine

2. Download Project Source Code

3. Download Data files

4
Lab: Intro to Python Jupyter Notebook Environment, Pandas, Matplotlib

Introduction to Python Development Environment, Pandas, NumPy, Matplotlib

5
Lab: AWS S3 Bucket Setup and Configure Security
  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
6
Summary

Summary of Introduction, Development Environment Setup and AWS Configuration

7
Introduction and House Keeping Quiz
8
Optional: Machine Learning Where To Start (Article)
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!
4.3
4.3 out of 5
763 Ratings

Detailed Rating

Stars 5
331
Stars 4
285
Stars 3
113
Stars 2
20
Stars 1
14
7e8dd21f2513053b82f37ad941a5dfc8
30-Day Money-Back Guarantee

Includes

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