10最好的Amazon Sagemaker教程推荐

Introduction and Housekeeping
SageMaker Housekeeping
Machine Learning Concepts
Model Performance Evaluation
SageMaker Service Overview
SageMaker Service and SDK Changes
XGBoost – Gradient Boosted Trees
Invoke Model Endpoint from External Clients
Endpoint Changes with Zero Downtime
Emerging AI Trends and Social Issues
Cloud Security and Access Management
Principal Component Analysis (PCA)
Recommender Systems – Factorization Machines
Model Optimization and HyperParameter Tuning
Time Series Forecasting – DeepAR
Anomaly Detection – Random Cut Forest
Artificial Intelligence (AI) Services
S3 Data Lake Architecture – Data Consolidation
Deep Learning and Neural Networks
Bring Your Own Algorithm
Storage for Servers
AWS – Support Plans and Feedback
Databases on AWS
On-Premises usage and other technologies
Practice Exam – AWS Certified Machine Learning Specialty
Other Resources

Introduction to Machine Learning
Introduction to AWS
Introduction to SageMaker
Setup
SageMaker Canvas Interface Walkthrough
Project 1 : Banknote Authentication
Project 2 : Spam SMS Detection
Project 3 : Customer Churn Prediction
Project 4 : Wine Quality Prediction
Assignment
Other Important Features in SageMaker Canvas
Congratulations & Next Steps

Introduction
Create AWS Account
Amazon Sagemaker
Ground Truth
Notebook
Processing
Training
Interface
Edge Manager
Augmented AI
AWS Marketplace
Conclusion
Introduction
Amazon Sagemaker
Conclusion

“Introduction, Success Tips & Best Practices and Key Learning Outcomes
Introduction to AI/ML, AWS and Cloud Computing
Project #1 – Employee Salary Predictions Using AWS SageMaker Linear Learner
Project #2 – Medical Insurance Premium Prediction
Project #3 – Retail Sales Prediction Using AWS SageMaker XGBoost (Regression)
Project #4 – Predict Cardiovascular Disease Using PCA & XGBoost (Classification)
Project #5 – Deep Learning for Traffic Sign Classification Using AWS SageMaker
Project #6 – SageMaker Studio DeepDive and AutoML”

“Amazon SageMaker: Introduction
Bring your own (Any) Tensorflow/Keras Docker container to SageMaker
Bring your own (Any) PyTorch BERT Docker Container
Bring Your own(Any) Algorithm in SageMaker
SageMaker Pre-built Algorithm
SageMaker Pre-built Algorithm: LogisticRegression
Model Deploy and Making Predictions
Create Pipeline, Workflow and schedule the SageMaker Notebook”

Introduction
Amazon Sagemaker & Built in Algorithm
Using your own Algorithm

“Introduction
********** PART 1: AWS & ML STARTER PACK!**********
Day 1: AWS Essentials Starter Pack – Part 1 (SignUp, Free Tier, Billing, & IAM)
Day 2: AWS Essentials Starter Pack – Part 2 (AI, ML, DL, DS, S3, & EC2)
Day 3: AWS Essentials Starter Pack – Part 3 (Amazon SageMaker)
********** PART 2: DATA LABELING IN AWS**********
Day 4: Labeling Data With AWS SageMaker GroundTruth
Day 5: Labeling Text, Bounding Boxes, and Semantic Segmentation in GroundTruth
********** PART 3: EXPLORATORY DATA ANALYSIS**********
Day 6: Exploratory Data Analysis (EDA) Part #1 – Crash Course on Pandas
Day 7: Exploratory Data Analysis (EDA) – Part #2 – Crash Course on Pandas
Day 8: Exploratory Data Analysis (EDA) – Part #3 – Crash Course on Pandas
Day 9: Exploratory Data Analysis (EDA) – Part #4 – Data Visualization
Day 10: Amazon SageMaker Data Wrangler
********** PART 4: MACHINE LEARNING REGRESSION**********
Day 11: Simple Linear Regression in Scikit-Learn
Day 12: Regression Using AWS SageMaker Linear Learner
Day 13: Multiple Linear Regression in Scikit-Learn
Day 14: Multiple Linear Regression with AWS SageMaker Linear Learner
Day 15: Launch ML Training Job from AWS Management Console (Regression)
Day 16: XG-Boost Regression in Scikit-Learn
Day 17: Built-in SageMaker XG-Boost Algorithm
Day 18: AWS SageMaker JumpStart
********** PART 5: HYPERPARAMETERS OPTIMIZATION**********
Day 19: Hyperparameters Optimization (GridSearch, Bayesian & Random)
Day 20: Hyperparameters Optimization in SageMaker
**********PART 6: MACHINE LEARNING CLASSIFICATION*********
Day 21: Classifiers – SVM, KNN, Logistic Regression, Naive Bayes, Random Forest
Day 22: XG-Boost Classification in AWS SageMaker
Day 23: K Nearest Neighbors (KNN) in SageMaker
Day 24: Classification Using AWS SageMaker Linear Learner
**********PART 7: AUTOML & NO-CODE ML **********
Day 25: No-Code ML – AutoGluon for Regression Type Problems
Day 26: No-Code ML – AutoGluon for Classification Type Problems
Day 27: No-Code ML – Amazon SageMaker Autopilot
Day 28: No-Code ML – AWS SageMaker Canvas for Classification & Regression Tasks
**********PART 8: MACHINE LEARNING WORKFLOWS**********
Day 29: Lambda Functions Using AWS Console
Day 30: Lambda Functions Using AWS SageMaker Boto3 SDK”

Introduction
Some more various built-in algorithms
Medical uses of Machine Learning using AWS Sagemaker and using a default model

Practice Tests

“Introduction
Hyperparameter Tuning
Deploying a Model, Creating Labeling Jobs, and more!”