How to navigate this guide

The order below should navigate the reader progressively through the topics that we will cover in the tutorials. The first section (1.2.0) is intended to build an understanding of machine learning fundamentals which will inform the following sections. Read the main links to articles, view/read but no need to try the code implementation examples, and for further learning - please see the references listed at the end.

1.2.0 General Machine Learning Best Practices

What is Machine Learning?
About Train, Validation and Test Sets in Machine Learning
Handling imbalanced datasets in machine learning
Model Optimization read Abstract and section II (first two paragraphs)
Parallel and Distributed Deep Learning read sections 1.2, 2, 3
Metrics to Evaluate your Machine Learning Algorithm

1.2.1 Classic Machine Learning (ML)

RandomForest

Random Forest Simple Explanation read sections: (1) Decision Tree: The Building Block and (2) From Decision Tree to Random Forest
Decision tree and RandomForest classifier in-depth for generic coding implementations
w/ sciki-learn for the specific function
RandomForest classifier in LULC case (Development Seed example)

LightGBM

LightGBM: A Highly Efficient Gradient Boosting Decision Tree read Introduction and section 2.1
LightGBM python library this is the library that we will use in the tutorial
LightGBM in crop type mapping case (Development Seed example and SentinelHub eo-learn example)

1.2.2 Deep learning

Deep Learning vs Classical Machine Learning

Deep Learning in a Nutshell – what it is, how it works, why care? read sections (1) What is Machine Learning? and (2) A First Look at Neural Networks

Semantic Segmentation

Semantic Segmentation with Deep Learning

TF dynamic UNet

UNet read sections 1 and 2
Dynamic UNet in LULC case (Development Seed example)

References:

Introduction to Statistical Learning book and examples written in python notebooks
Additional Examples from Python for Data Science