This document outlines an agenda for a machine learning workshop. The agenda includes an introduction to machine learning at AWS, an overview of the machine learning process, and details about the workshop layout and outcomes. It describes a business use case for predicting car evaluations based on attributes like price and safety features. It provides details about the features, sample data, and the machine learning approach using Amazon SageMaker's XGBoost algorithm. It also outlines the workshop execution plan, which is divided into three parts: data preparation and ingestion, machine learning process and pipeline, and machine learning inference.
6. AI SERVICES
AMAZON
POLLY
AMAZON
TRANSCRIBE
AMAZON
TRANSLATE
AMAZON
COMPREHEND
AMAZON
LEX
AMAZON
REKOGNITION
VIDEO
AMAZON
FORECAST
AMAZON
PERSONALISE
AMAZON
REKOGNITION
IMAGE
Vision Speech Language Chatbots Forecasting
AMAZON
TEXTRACT
Recommendations
(App developers with
little knowledge of ML)
AMAZON
SAGEMAKER
BUILD TRAIN DEPLOY
Pre-built algorithms and notebooks
Data labelling (AMAZON GROUND TRUTH)
One-click model training and tuning
Optimisation (AMAZON NEO)
One-click deployment and hostingML SERVICES
Reinforcement learning
Algorithms and models
(AWS MARKETPLACE FOR MACHINE LEARNING)
AWS
DEEP RACER
AWS
DeepLens
(ML developers
and data scientists)
Optimised
Frameworks
ML FRAMEWORKS AND
INFRASTRUCTURE
Interfaces Infrastructure
AMAZON
EC2 P3
& P3dn
AMAZON
EC2 C5
FPGAs AWS IOT
GREENGRASS
AMAZON
ELASTIC
INFERENCE
(ML researchers and academics)
AMAZON
INFERENTIA
The Amazon ML stack: Broadest and deepest set of capabilities