Practical Data Science on the AWS Cloud Specialization

Description

This repository is a collection of notes documenting the essential teachings in the Practical Data Science on AWS Cloud Specialization on Coursera. It is an easy reference to come back to for review and includes experimental notebooks for exploration and better understading of the concepts.

Studying Framework

A framework I find useful to learn content, especially in online courses, is the following:

1. Essentials: Take notes on the essential concepts and ideas.
2. Explain: Explain the concepts and ideas in your own words to an inanimate object (e.g. a rubber duck) to ensure you understand them.
3. Consistent: Nothing beats the exponential power of consistency.

In short: consistently explain the essentials. Anything else, such as applying what you learn by building projects, will come easier when the foundation is built with this framework - this is true for me at least.

Structure of Specialization

1. Analyze Datasets and Train ML Models using AutoML
2. Build, Train, and Deploy ML Pipelines using BERT
3. Optimize ML Models and Deploy Human-in-the-Loop ML Pipelines

Notes

1. Analyze Datasets and Train ML Models using AutoML

Week 1.1

The cloud allows us to not be limited by our local resources and hardware. It allows us to scale up and down as needed.

In progress...