Section 1 : Introduction and Housekeeping
Lecture 1 Introduction copy 00:03:03 Duration
Lecture 2 Overview - AWS Machine Learning Specialty Exam 00:09:05 Duration
Lecture 3 Preparation - AWS Machine Learning Specialty Exam 00:04:21 Duration
Lecture 4 AWS Account Setup, Free Tier Offers, Billing, Support 00:07:00 Duration
Lecture 5 Billing Alerts, Delegate Access 00:08:10 Duration
Lecture 6 Configure IAM Users, Setup Command Line Interface (CLI) 00:11:30 Duration
Lecture 7 Benefits of Cloud Computing 00:06:12 Duration
Lecture 8 AWS Global Infrastructure Overview 00:05:58 Duration

Section 2 : SageMaker Housekeeping
Lecture 1 Lab - S3 Bucket Setup 00:02:53 Duration
Lecture 2 Lab - Setup SageMaker Notebook Instance 00:02:49 Duration
Lecture 3 Lab - Source Code Setup 00:02:26 Duration

Section 3 : Machine Learning Concepts
Lecture 1 Introduction to Machine Learning, Concepts, Terminologies 00:10:23 Duration
Lecture 2 Data Types - How to handle mixed data types 00:12:42 Duration
Lecture 3 Introduction to Python Notebook Environment 00:10:33 Duration
Lecture 4 Introduction to working with Missing Data 00:09:35 Duration
Lecture 5 Data Visualization - Linear, Log, Quadratic and More 00:04:38 Duration

Section 4 : Model Performance Evaluation
Lecture 1 Introduction 00:03:26 Duration
Lecture 2 Regression Model Performance 00:09:58 Duration
Lecture 3 Binary Classifier Performance 00:08:00 Duration
Lecture 4 Binary Classifier - Confusion Matrix 00:06:56 Duration
Lecture 5 Binary Classifier - SKLearn Confusion Matrix 00:03:18 Duration
Lecture 6 Binary Classifier - Metrics Definition 00:03:52 Duration
Lecture 7 Binary Classifier - Metrics Calculation 00:04:26 Duration
Lecture 8 Binary Classifier - Area Under Curve Metrics 00:09:40 Duration
Lecture 9 Multiclass Classifier 00:12:36 Duration

Section 5 : SageMaker Service Overview
Lecture 1 Introduction to SageMaker 00:04:54 Duration
Lecture 2 Instance Type and Pricing 00:10:21 Duration
Lecture 3 DataFormat 00:11:12 Duration
Lecture 4 SageMaker Built-in Algorithms 00:09:36 Duration
Lecture 5 Popular Frameworks and Bring Your Own Algorithm 00:05:24 Duration

Section 6 : XGBoost - Gradient Boosted Trees
Lecture 1 Introduction to XGBoost 00:08:53 Duration
Lecture 2 Lab - Data Preparation Simple Regression
Lecture 3 Lab - Training Simple Regression 00:12:25 Duration
Lecture 4 Lab - Data Preparation Non-linear Data set 00:02:39 Duration
Lecture 5 Lab - Training Non-linear Data set 00:04:48 Duration
Lecture 6 Lab - Data Preparation Bike Rental Regression 00:08:24 Duration
Lecture 7 Lab - Train Bike Rental Regression Model 00:06:10 Duration
Lecture 8 Lab - Train using Log of Count 00:04:14 Duration
Lecture 9 Lab - How to train using SageMaker's built-in XGBoost Algorithm 00:07:36 Duration
Lecture 10 Lab - How to run predictions against an existing SageMaker Endpoint 00:04:29 Duration
Lecture 11 SageMaker Endpoint Features 00:05:41 Duration
Lecture 12 Lab - Multi-class Classification 00:05:41 Duration
Lecture 13 Lab - Binary Classification 00:06:22 Duration
Lecture 14 HyperParameter Tuning, Bias-Variance, Regularization (L1, L2) 00:11:08 Duration

Section 7 : Invoke Model Endpoint From External Clients
Lecture 1 Integration Overview 00:02:32 Duration
Lecture 2 Client to Endpoint using SageMaker SDK 00:09:26 Duration
Lecture 3 Client to Endpoint using Boto3 SDK 00:03:51 Duration
Lecture 4 Microservice - Lambda to Endpoint - Payload 00:03:24 Duration
Lecture 5 Microservice - Lambda to Endpoint 00:09:10 Duration
Lecture 6 Microservice - API Gateway, Lambda to Endpoint 00:10:34 Duration

Section 8 : SageMaker - Principal Component Analysis (PCA)
Lecture 1 Introduction to Principal Component Analysis (PCA) 00:05:49 Duration
Lecture 2 PCA Demo Overview 00:01:16 Duration
Lecture 3 Demo - PCA with Random Dataset 00:03:29 Duration
Lecture 4 Demo - PCA with Correlated Dataset 00:05:26 Duration
Lecture 5 Demo - PCA with Kaggle Bike Sharing - Overview and Normalization 00:03:52 Duration
Lecture 6 Demo - PCA Local Mode with Kaggle Bike Train 00:03:31 Duration
Lecture 7 Demo - PCA training with SageMaker 00:04:23 Duration
Lecture 8 Demo - PCA Projection with SageMaker 00:02:42 Duration
Lecture 9 Summary 00:01:22 Duration

Section 9 : Recommender Systems - Factorization Machines
Lecture 1 Introduction to Factorization Machines 00:05:59 Duration
Lecture 2 Demo - Movie Recommender Data Preparation 00:10:35 Duration
Lecture 3 Demo - Movie Recommender Model Training 00:05:35 Duration
Lecture 4 Demo - Movie Predictions By User 00:07:10 Duration

Section 10 : Model Optimization and HyperParameter Tuning
Lecture 1 Introduction to Hyperparameter Tuning 00:06:11 Duration
Lecture 2 Lab Tuning Movie Rating Factorization Machine Recommender System 00:18:05 Duration
Lecture 3 Lab Step 2 Tuning Movie Rating Recommender System 00:05:01 Duration
Lecture 4 HyperParameter, Bias-Variance, Regularization (L1, L2) [Repeat from XGBoost] 00:11:08 Duration

Section 11 : Time Series Forecasting - DeepAR
Lecture 1 Introduction to DeepAR Time Series Forecasting 00:09:47 Duration
Lecture 2 DeepAR Training and Inference Formats 00:09:49 Duration
Lecture 3 Working with Time Series Data, Handling Missing Values 00:09:59 Duration
Lecture 4 Demo - Bike Rental as Time Series Forecasting Problem 00:11:44 Duration
Lecture 5 Demo - Bike Rental Model Training 00:07:21 Duration
Lecture 6 Demo - Bike Rental Prediction 00:04:50 Duration
Lecture 7 Demo - DeepAR Categories 00:06:10 Duration
Lecture 8 Demo - DeepAR Dynamic Features Data Preparation 00:06:34 Duration
Lecture 9 Demo - DeepAR Dynamic Features Training and Prediction
Lecture 10 Summary 00:01:16 Duration

Section 12 : Anomaly Detection - Random Cut Forest
Lecture 1 Introduction to Random Cut Forest and Intuition Behind Anomaly Detection
Lecture 2 Lab - Taxi Passenger Traffic Analysis (AWS Provided Example) 00:08:53 Duration
Lecture 3 Lab - Auto Sales Analysis 00:05:55 Duration

Section 13 : Artificial Intelligence (AI) Services
Lecture 1 Introduction 00:03:15 Duration
Lecture 2 2.1 Amazon Transcribe and Lab 00:05:33 Duration
Lecture 3 2.2 Amazon Transcribe and Lab 00:06:35 Duration
Lecture 4 3. Amazon Translate 00:04:29 Duration
Lecture 5 4.1 Amazon Comprehend 00:05:43 Duration
Lecture 6 4.2 Amazon Comprehend 00:05:00 Duration
Lecture 7 4.3 Amazon Comprehend training 00:08:35 Duration
Lecture 8 5. Amazon Polly 00:04:16 Duration
Lecture 9 6. Amazon Lex
Lecture 10 7. Amazon Rekognition 00:08:21 Duration
Lecture 11 8. Amazon Textract & Summary 00:03:03 Duration

Section 14 : S3 Data Lake Architecture - Data Consolidation
Lecture 1 Introduction to Data Lake 00:10:28 Duration
Lecture 2 Kinesis - Streaming and Batch Processing 00:05:24 Duration
Lecture 3 Data Formats and Tools for Data Format Conversion 00:08:34 Duration
Lecture 4 In-Place Analytics and Portfolio of Tools 00:05:02 Duration
Lecture 5 Monitoring and Optimization 00:06:27 Duration
Lecture 6 Security and Protection 00:06:37 Duration
Lecture 7 Lab – Glue Data Catalog 00:08:31 Duration
Lecture 8 Lab - Query with Athena 00:02:01 Duration
Lecture 9 Lab - Glue ETL - Convert format to Parquet 00:04:43 Duration
Lecture 10 Lab - Query Amazon Customer Reviews with Athena 00:05:06 Duration
Lecture 11 Lab – Sentiment of the Customer Review 00:06:07 Duration
Lecture 12 Lab - Query Sentiment of Customer Reviews using Athena 00:04:17 Duration
Lecture 13 Lab – Serverless Customer Review Solution Part 1 00:09:45 Duration
Lecture 14 Lab – Serverless Customer Review Solution Part 2 00:07:52 Duration

Section 15 : Deep Learning and Neural Networks
Lecture 1 Concepts - Gradient Descent, Loss Function for Regression 00:14:12 Duration
Lecture 2 Concepts - Gradient Descent, Loss Function for Classification 00:10:02 Duration
Lecture 3 Neural Networks and Deep Learning 00:07:35 Duration
Lecture 4 Lab - Regression with SKLearn Neural Network 00:06:38 Duration
Lecture 5 Lab - Regression with Keras and TensorFlow 00:07:24 Duration
Lecture 6 Lab - Binary Classification - Part 1- Customer Churn Prediction 00:05:59 Duration
Lecture 7 Lab - Binary Classification - Part 2 - Customer Churn Prediction 00:07:32 Duration
Lecture 8 Lab - Multiclass Classification - Iris 00:04:48 Duration

Section 16 : Bring Your Own Algorithm
Lecture 1 Introduction and How built-in algorithms work 00:05:06 Duration
Lecture 2 Custom Image and Popular Framework 00:03:55 Duration
Lecture 3 Folder Structure and Environment Variables 00:07:19 Duration
Lecture 4 Lab - SKLearn Estimator Bring Your Own Part 1 00:09:22 Duration
Lecture 5 Lab - SKLearn Estimator Bring Your Own Part 2 00:08:15 Duration
Lecture 6 Lab - TensorFlow Estimator Bring Your Own 00:03:51 Duration

Section 17 : Storage for Servers
Lecture 1 Introduction to Storage 00:08:40 Duration
Lecture 2 Elastic Block Store (EBS) 00:13:09 Duration
Lecture 3 Elastic File System, FSx for Windows, FSx for Lustre 00:04:53 Duration

Section 18 : AWS - Support Plans and Feedback
Lecture 1 How to contact AWS for Production Support 00:07:14 Duration

Section 19 : Databases on AWS
Lecture 1 AWS Databases - Introduction, Benefits, and Types
Lecture 2 Relational Database Service (RDS) - Features and Benefits 00:12:41 Duration
Lecture 3 Aurora and Aurora Serverless Relational Database 00:04:47 Duration
Lecture 4 DynamoDB - Primary Key, Partitions, and Features 00:08:03 Duration
Lecture 5 Cassandra and DocumentDB 00:02:30 Duration
Lecture 6 Amazon ElastiCache - Usage Example, Features 00:05:30 Duration
Lecture 7 Amazon Redshift 00:02:26 Duration