-
1. Introduction to Housekeeping
-
Introduction
-
increase the speed of learning
-
Preparation - AWS Machine Learning Specialty Exam
-
Lab - AWS Account Setup, Free Tier Offers, Billing, Support
-
Lab - Billing Alerts, Delegate Access
-
Lab - Configure IAM Users, Setup Command Line Interface (CLI)
-
Benefits of Cloud Computing
-
AWS Global Infrastructure Overview
-
-
2. Sege Maker Housekeeping
-
3. Machine Learning Concepts
-
Introduction to Machine Learning, Concepts, Terminologies
-
Data Types - How to handle mixed data types
-
Lab - Python Notebook Environment
-
Lab - Working with Missing Data
-
Lab - Data Visualization - Linear, Log, Quadratic and More
-
AWS Sample Question #2
-
Answer to Question #2
-
AWS Sample Question #9
-
Answer to Sample Question #9
-
-
4. Model Performance Evaluvation
-
Introduction
-
Model Performance
-
Downloadable Resources
-
Lab - Binary Classifier Performance
-
Lab - Binary Classifier - Confusion Matrix
-
Lab - Binary Classifier - SKLearn Confusion Matrix
-
Binary Classifier - Metrics Calculation
-
Binary Classifier - Metrics Definition
-
Question - Why not Model 1?
-
Binary Classifier - Area Under Curve Metrics
-
Lab - Multiclass Classifier
-
Model Performance
-
Model Performance Evaluation
-
What metric is appropriate - Q&A Discussion
-
AWS Sample Question #5 Answer to Question #5
-
Answer to Question #5
-
-
5. SegeMaker Service Overview
-
Downloadable Resources
-
How is AWS SageMaker different from other ML frameworks?
-
Introduction to SageMaker
-
Instance Type and Pricing
-
Save Money on SageMaker Usage
-
DataFormat
-
SageMaker Built-in Algorithms
-
Popular Frameworks and Bring Your Own Algorithm
-
Infrastructure, Pricing, Support - Review
-
AWS Sample Question #1
-
Answer for Sample Question #1
-
AWS Sample Question #10
-
Answer for Sample Question #10
-
What does a data scientist in gaming do? By Carly Taylor
-
-
6. SegeMaker Service and SDK Changes
-
7. XGBoost - Gradient Boosted Trees
-
Downloadable Resources
-
Introduction to XGBoost
-
Lab - Data Preparation Simple Regression
-
Lab - Training Simple Regression
-
Lab - Data Preparation Non-linear Data set
-
Lab - Training Non-linear Data set
-
Exercise - Improving quality of predictions
-
Lab - Data Preparation Bike Rental Regression
-
Lab - Train Bike Rental Regression Model
-
Lab - Train using Log of Count
-
ResourceLimitExceeded Error - How to Increase Resource Limit
-
Lab - How to train using SageMaker's built-in XGBoost Algorithm
-
Q&A: How does SageMaker built-in know the target variable?
-
Lab - How to run predictions against an existing SageMaker Endpoint
-
Q&A - XGBoost on SageMaker predicted values are not delimited consistently
-
SageMaker Endpoint Features
-
SageMaker Spot Instances - Save up to 90% for training jobs
-
Lab - Multi-class Classification
-
Lab - Binary Classification
-
Exercise - Improve Data Quality in Diabetes dataset
-
Question on Diabetes Data Quality Improvement
-
Question on Diabetes model - is group mean on target the right approach?
-
Data Leakage
-
Exercise - Mushroom Classification
-
Quiz - XGBoost
-
8 questions
-
Underfitting, Overfitting
-
3 questions
-
AWS Sample Question #8
-
Answer to AWS Sample Question #8
-
-
8. Invoke Model Endpoint from External Clients
-
Install SageMaker SDK, GIT Client, Source Code, Security Permissions
-
IAM users for the lab Integration Overview
-
Lab - Client to Endpoint using SageMaker SDK
-
Lab - Client to Endpoint using Boto3 SDK
-
Microservice - Lambda to Endpoint - Payload
-
Lambda UI Changes
-
Lab - Microservice - Lambda to Endpoint
-
API Gateway - UI Changes
-
Lab - API Gateway, Lambda, Endpoint
-
-
9. EndPoint Changes with Zero Downtime
-
10. Emerging Ai Trends and Social issues
-
11. Cloud Security and Access Management
-
Introduction
-
Shared Responsibility Model, Compliance, Delegation, Federation
-
Credentials, MFA, Identity-based, Resources-based Policy
-
Inline and Managed Policy, Amazon Resource Naming (ARN) Convention
-
Principal, Effect, Action, Resource, Not Clause
-
Conditional Access, Implicit Deny, Explicit Allow and Deny, Permission Boundary
-
IAM Roles, Cross-account access options
-
Federation, SSO, SAML, Active Directory, AWS Organizations, Cognito
-
Lab - Identity-based policy, Implicit Deny, Explicit Allow
-
Lab - Policy Generator, Managed Policy, Versions, Groups
-
Lab - Resource-based policy, Policy Generator, Principals
-
Cloud Security
-
-
12. Principal Component Analysis (PCA)
-
Normalization and Standardization
-
Downloadable Resources
-
Introduction to Principal Component Analysis
-
PCA Demo Overview
-
Demo - PCA with Random Dataset
-
Demo - PCA with Correlated Dataset
-
Cleanup Resources on SageMaker
-
Demo - PCA with Kaggle Bike Sharing - Overview and Normalization
-
Demo - PCA Local Mode with Kaggle Bike Train
-
Demo - PCA training with SageMaker
-
Demo - PCA Projection with SageMaker
-
Exercise : Kaggle Bike Train and PCA
-
Summary
-
-
13. Recommender Systems - Factorization Machines
-
14. Model Optimization and HyperParameter Tuning
-
Downloadable Resources
-
Introduction to Hyperparameter Tuning
-
Lab: Tuning Movie Rating Factorization Machine Recommender System
-
Lab: Step 2 Tuning Movie Rating Recommender System
-
HyperParameter, Bias-Variance, Regularization (L1, L2) [Repeat from XGBoost]
-
Nuts and Bolts of Optimization
-
Model Optimization
-
Model Optimization - related question
-
-
15. Time Series Forecasting - DeepAR
-
Downloadable Resources
-
Introduction to DeepAR Time Series Forecasting
-
DeepAR Training and Inference Formats
-
Working with Time Series Data, Handling Missing Values
-
Demo - Bike Rental as Time Series Forecasting Problem
-
Demo - Bike Rental Model Training
-
Demo - Bike Rental Prediction
-
Demo - DeepAR Categories
-
Demo - DeepAR Dynamic Features Data Preparation
-
Demo - DeepAR Dynamic Features Training and Prediction
-
Summary
-
Question: How to train a model for different products using DeepAR?
-
-
16. Anomaly Detection - Random Cut Forest
-
17. Artificial Intelligence (A) Services
-
Downloadable Resources
-
Lab Instructions
-
1. Introduction
-
2.1 Amazon Transcribe and Lab
-
2.2 Amazon Transcribe and Lab
-
3. Amazon Translate Translate - Practical Scenario
-
4.1 Amazon Comprehend Pricing Comprehend
-
4.2 Amazon Comprehend
-
4.3 Amazon Comprehend training
-
5. Amazon Polly
-
7. Amazon Rekognition
-
6. Amazon Lex
-
8. Amazon Textract & Summary AI Services Quiz
-
-
18. S3 Data Lake Architecture - Data Consolidation
-
Downloadable Resources
-
Lab Instructions
-
Introduction to Data Lake
-
Kinesis - Streaming and Batch Processing
-
Data Formats and Tools for Data Format Conversion
-
In-Place Analytics and Portfolio of Tools
-
Monitoring and Optimization
-
Security and Protection
-
Quiz - Data Lake
-
Lab Instructions - Glue Data Catalog
-
Lab – Glue Data Catalog
-
Lab Instructions – Athena In-place Querying
-
Lab - Query with Athena
-
Lab - Glue ETL - Convert format to Parquet
-
Lab - Query Amazon Customer Reviews with Athena
-
Lab – Sentiment of the Customer Review
-
Lab - Query Sentiment of Customer Reviews using Athena
-
Lambda UI Changes
-
Lab – Serverless Customer Review Solution Part 1
-
Lab – Serverless Customer Review Solution Part 2
-
AWS Sample Question #3
-
Answer to Sample Question #3
-
-
19. Deep Learning and Neural Networks
-
ReadMe and Downloadable Resources
-
Regression - Gradient Descent Batch, Mini-Batch, Stochastic, Loss, RMSProp, Adam
-
Classification - Gradient Descent, Loss Function
-
Neural Networks and Deep Learning
-
Real World Face Restoration
-
Lab - Regression with SKLearn Neural Network
-
Lab - Regression with Keras and TensorFlow
-
Customer Churn Data
-
Lab - Binary Classification - Part 1- Customer Churn Prediction
-
Lab - Binary Classification - Part 2 - Customer Churn Prediction
-
Lab - Multiclass Classification - Iris
-
Transfer Learning
-
Optimizing for GPUs
-
Multi-Class Multi-Label Classification
-
Nuts and Bolts of Optimization [Repeat]
-
Quiz - Neural Network and Model Tuning
-
Answer to Sample Question #4
-
AWS Sample Question #4
-
AWS Sample Question #6
-
Answer to Sample Question #6
-
AWS Sample Question #7
-
Answer to Sample Question #7
-
MIT - Introduction to Deep Learning
-
Convolutional Neural Network (CNN)
-
Recurrent Neural Networks (RNN), LSTM
-
Generative Adversarial Networks (GANs)
-
-
20. Bring Your Own Algorithm
-
How to use TensorFlow, Pytorch, SKLearn in SageMaker
-
Downloadable Resources
-
Introduction and How built-in algorithms work
-
Custom Image and Popular Framework
-
Folder Structure and Environment Variables
-
Lab - SKLearn Estimator Bring Your Own Part 1
-
Lab - SKLearn Estimator Bring Your Own Part 2
-
Lab - TensorFlow Estimator Bring Your Own
-
-
21. Storage for Servers
-
22. AWS - Support Plans and Feedback.
-
23. Databases on AWS
-
Downloadable Resources
-
AWS Databases - Introduction, Benefits, and Types
-
Relational Database Service (RDS) - Features and Benefits
-
Aurora and Aurora Serverless Relational Database
-
DynamoDB - Primary Key, Partitions, and Features
-
Cassandra and DocumentDB
-
Amazon ElastiCache - Usage Example, Features
-
Amazon Redshift
-
-
24. On-Premises usage and other technologies
-
25. Practice Exam - AWS Certified Machine Learning Specialty
