# Getting Started

Get a brief overview of the course and its prerequisites.

## We'll cover the following

## Course overview

**Graph machine learning**, as the name suggests, is a field that involves performing machine learning on graph data structures. Graphs are used to represent complex relationships between objects, and they are ubiquitous in fields such as social networking, bioinformatics, recommender systems, and natural language processing.

This course is designed for anyone who wants to understand graph machine learning concepts and techniques comprehensively. You'll learn how to build different types of graphs, apply state-of-the-art graph machine learning techniques, understand graph neural networks, and perform various graph analytics-related tasks.

The course will include both theoretical and coding components. You'll learn how to apply graph machine learning concepts to real-world problems using practical examples.

## Prerequisites

The following are the pre-intermediate-level requisites for the course:

A good understanding of linear algebra and calculus.

Familiarity with data structures and algorithms.

General knowledge of machine learning concepts, such as supervised and unsupervised learning.

Proficiency in at least one programming language. (Python is recommended.) The courses: Learn to Code: Python for Absolute Beginners and Python 101: Interactively learn how to program with Python 3, can be of great help in learning the concepts.

## Target audience

The course assumes no prior knowledge of graph machine learning but requires proficiency in Python programming and general knowledge of machine learning concepts. The course will provide a comprehensive introduction to graph machine learning, but it's not intended to cover advanced topics in depth. So, the target audience for this course will be learners who want to explore the intermediate-level concepts of graph machine learning.