I’m going through the Udemy course Complete Machine Learning and Data Science: Zero to Mastery.

The course runs under the flag of Andrei Neagoie. Andrei is a popular instructor on Udemy, with almost 200.000 students, and top reviews.
For this course, he has paired up with Daniel Bourke, a self-taught Machine Learning Engineer from Australia.

In this blog post series, I will jot down my thoughts on the course, and what I’ve learned.

I have zero knowledge of Data Science and Machine Learning. The course promises to teach you both topics from scratch. We’ll see how it holds up.

This is the first part of the blog post series.

1. Introduction

The section covers the course outline and how to join the learning community for the course.

What I liked:

The course is structured like a story. You are hired as a data science engineer at a fictional company. During the course, you have to carry out tasks for your boss.

I enjoyed the tongue-in-cheek setup. The storytelling experience helps with making learning more fun.

2. Machine Learning 101

The section provides an approachable explanation of what Machine Learning is.

The goal of Machine Learning is to make machines act more and more like humans because the smarter they get, the more they help us humans accomplish our goals.

Differences between Narrow A.I. and General A.I.:
Currently, we only have Narrow A.I.: A machine (Artificial Intelligence) can do one thing exceptionally well.
General A.I. (like humans, the A.I. would have several abilities) is still far away.

Machine Learning is a subset of A.I.

Machine Learning is an approach to try and achieve artificial intelligence through systems that can find patterns trough a set of data.

Deep Learning is one of the techniques for implementing Machine Learning.

What is Data Science?

There’s a lot of overlap between Machine Learning and Data Science (analyze data and help achieve a business goal).

The section also shows a practical, simple example of Machine Learning. This lecture offers a useful application of the main concepts of Machine Learning.

I liked how Andrei explains how we moved from spreadsheets (CSV) to relational databases (SQL), to “Big Data” (NoSQL), to make business decisions.
Machine Learning is an attempt to make use of massive amounts of data. (The why? of Machine Learning)

Machine Learning is about predicting results based on incoming data.

Interestingly, the course repeats the previous material with explanations from the second instructor, Daniel. The short video provides a different perspective.


So far, the course impresses with offering an approachable, beginner-friendly way to get into a difficult topic.

Even though the first two sections are theoretical, the instructors manage to lighten them up with exercises.

They also encourage you to recap and to repeat the material.

The next part in th series is here: part 2

Go to the other parts of the series: