Getting started with Machine Learning on AWS.
summary
Walks through the AWS ML stack with live console and SDK demos: Amazon Rekognition (face, celebrity, text, moderation, PPE detection), Amazon Polly with SSML, real‑time Amazon Transcribe and Translate, and Amazon Textract extracting tables and form fields. Shows Amazon Personalize workflow and a hands‑on Amazon SageMaker demo training XGBoost on the 506‑sample Boston housing set (training stops around 37 rounds), deploying an endpoint, and using S3, Studio and spot instances to cut training costs up to ~75%. Useful if you want actionable how‑to steps and reproducible pipelines.
AI-written summary · about
chapters (17)
- 0:00Introduction and welcome
- 1:07What is machine learning
- 3:37AI vs machine learning vs deep learning
- 8:18Supervised vs unsupervised learning
- 16:45Machine learning cycle explained
- 20:16Getting started with ML projects
- 35:14AWS machine learning overview
- 42:56AI services on AWS
- 51:51Text to speech with Amazon Polly
- 57:38Speech to text with Amazon Transcribe
- 1:00:32Translation with Amazon Translate
- 1:03:50Document text extraction with Textract
- 1:08:06Recommendations with Amazon Personalize
- 1:13:25Machine learning services with SageMaker
- 1:22:10SageMaker demo with XGBoost
- 1:37:14Frameworks and infrastructure options
- 1:39:40Resources and closing
related talks
55mMachine Learning and AI in Java on AWS
54mMachine Learning for Developers
44mPragmatic Machine Learning in the Cloud
31mProductizing Machine Learning over Big Data with AWS tools
39mUsing AWS Artificial Intelligence services with Python
19mUsing Amazon SageMaker to develop and deploy ML models
51mProfundizando en Aprendizaje Automático para Desarrolladores
37mStreamlining Machine Learning Operations