• Ref: https://www.udemy.com/course/aws-ai-practitioner-certified/learn/lecture/44887763 and https://www.udemy.com/course/aws-ai-practitioner-certified/learn/lecture/47890573
• Contents:

Overview

Definition

• 🔧 Fully-managed service for developers/data scientists to build and deploy ML models
  • 💡 Typically, difficult to do all the processes in one place + provision servers
  • Example: predicting your AWS exam score

End-to-end ML service

1. Collect and prepare data
2. Build and train ML models
3. Deploy the models and monitor the performance of the predictions

• Diagram

Built-in Algorithms

1. Supervised Algorithms
   • Linear regressions
   • Classifications
     • e.g. KNN Algorithms
2. Unsupervised Algorithms
   • Principal Component Analysis (PCA) – reduce number of features
     • Diagram
   • K-means – find grouping within data
   • Anomaly Detection
3. Textual Algorithms – NLP, summarization…
4. Image Processing Algorithms – classification, detection…
5. Forecasting Algorithms (e.g. DeepAR - forecasts time-series data with RNN)

💡 More built-in models and algorithms than Amazon Bedrock's FMs → wider selection