Complete Machine Learning Guide – From Zero to Hero in ML

Today, Machine Learning(ML) is a very hot skill to have and everyone is looking for a step by step way to at least become reasonably good at ML. So, in this blog I will take you through a brief tour of Machine Learning and its concepts.

At the end, I will give you an Ultimate 3 Months Curriculum with the best courses on ML present online structured in a proper way and 6 projects which will give you sufficient amount of knowledge and experience in Machine Learning (Though you have to do a lot more projects to call yourself a ML Developer).

What is Machine Learning?

Machine Learning(ML) is a direct application of Artificial Intelligence(AI) and as the name suggests, ML is the ability of a system to automatically learn and improve from experience without being explicitly programmed. Basically, it is giving the human like learning and improving ability to a machine.

Credits: Edureka

The learning process begins with observations or data, such as examples, direct experience, or instruction, in order to look for patterns in data and make better decisions in the future based on the examples that we provide. The primary aim of Machine Learning is to allow the computers learn automatically without human intervention or assistance.
The twist here is that Machine Learning completely depends on the data available, as said in the joke below, if the data is biased towards wrong thing, ML will give wrong output only. It doesn’t have that thinking capability which humans does. That’s the difference between ML and AI and that is why ML comes under AI.

A Random Machine Learning Joke ๐Ÿ™‚
If everyone is jumping off a cliff, Machine Learning says Jump.

Before diving into some complex stuff, let us look at some facts and stats of Machine Learning which every ML enthusiast must know.
Firstly, Facts and Info:
1. It was in 1950s when first machine learning research was conducted using simple algorithms though some of the theorems trace back to 18th century.
2. Machine Learning was first commercialized in 1989 Axcelis, Inc. releases Evolver, the first software package to commercialize the use of genetic algorithms on personal computers.
3. First considerable achievement in ML was when a Machine Played Backgammon in 1992. Gerald Tesauro developed TD-Gammon, a computer backgammon program that used an artificial neural network trained using temporal-difference learning.
4. Today, there are state-of-the-art machine learning algorithms which can beat masters in games like Chess and Go. Recently, a ML from Facebook and CMU has gone beyond everyone’s expectations and have defeated champs in poker.

Machine learning will automate jobs that most people thought could only be done by people.
-Dave Waters

Now, Some Stats:
$28.5 billion is the total funding allocated to machine learning worldwide during the first quarter of 2019. (source:
2. $120 billion is the estimated global sales of AI-powered hardware by the end of 2025.(source:
3. $13 trillion is the potential global economic that AI & ML could deliver by 2030. (source:
4. 49% of companies are already exploring or planning to use ML. (source:
97% of mobile users use AI-powered voice assistants. (source:
6. 14x is the rate of increase in the number of AI & ML startups since the year 2000. (source:
After seeing these stats, I hope you might have understood why everyone is running behind ML and AI. More Stats on ML
The only problem with ML is that it will make a lot of people jobless…..

Machine Learning Applications

As said above, machine learning is already being explored and used by a lot businesses across the world. So, let us have a look at various kinds of applications and fields where ML can be used and let us also have a look on some interesting ML applications. (These might give you some project ideas after you learn ML).
Some Top Uses of ML:
1. Virtual Personal Assistants.(Google Assistant, Siri, Alexa)
Recommender and Dynamic Pricing Systems. (Found on sites like Amazon)
3. Spam and Fraud Detection
4. Search Engines
5. Robotics
6. Surveillance (CCTV monitoring by ML)
7. Self Driving Cars
8. Social Media (Ads, Face Recognition etc)
9. Transport Assistance (Traffic prediction, price estimation by services like Uber etc.)
10. Marketing, Risk Management, Investing, Sales, Ads, Recruitment …… and the lost goes on.

How a few companies are using ML in their services
1. Netflix uses Machine Learning that which learns the user behaviour and gives best possible recommendations.
2. Tinder uses ML for its new feature โ€˜Smart Photosโ€™, which increases a userโ€™s chances of finding a match.
Oval Money offers users different easy-to-follow strategies that will help people avoid extra spending.
4. Snapchatโ€™s filters are the best possible examples for the combination of augmented reality and machine learning algorithms for computer vision.
5. Google maps employs machine learning to make the process of choosing a parking spot much easier.
6. ImprompDo helps people by removing the problem of scheduling. ML gives it an opportunity to discover suitable moments for showing push notifications.
7. Dango uses machine learning to solve the biggest worldโ€™s problem like finding a perfect emoji ๐Ÿ™‚ …

Types of ML

Generally speaking, there are 3 types of ML (Though there are a lot other classifications and types, this is the most basic one). They are:
1. Supervised Learning
2. Unsupervised Learning
3. Reinforcement Learning

types of machine learning

I am not going into depth of the types of machine learning. For the people who are curious i recommend reading this blog titled “What are the types of machine learning?“. This blog have really good information on Types of Machine Learning.

The Ultimate 3 Months Curriculum

So, here is the ultimate 3 months curriculum which will make you pretty good at machine learning even if you do not know anything about it. (Disclaimer: You need to work hard to finish this curriculum and become good at ML, it is not that easy ๐Ÿ™‚ )

Month 1 – The Math Month

Let me tell you that Mathematics is at the core of ML and you need to be pretty strong at math. Without a good foundation of math you cannot succeed in ML. So, for the first month we will work only on important math concepts.

Week 1 – Linear Algebra

Here are two wonderful resources from where you can learn Linear Algebra.
1. A YouTube Playlist titled the Essence of Linear Algebra (or)
2. A Linear Algebra online course by MIT.

MIT Linear Algebra course

Week 2 – Calculus

A YouTube Playlist titled the Essence of calculus

Week 3 – Probability

A Free Probability course on edX by MIT

edX Probability course

Week 4 – Algorithms

A Free Algorithms course on edX by University of Pennsylvania

Algorithms course on edX

There is one single course on edX by Microsoft titled “Essential Math for Machine Learning: Python Edition“. This single course covers all the above topics but not in that much detail, so, I would highly recommend not to go with a single course and do these topic separately as every topic is a ocean in itself.

Month 2 – Getting into ML

Congratulations, you have completed our math month and now you have really good grip on math needed for Machine Learning. Now, let us first learn python which is the most popular language used for ML. After python we will go into ML and algorithms for ML.

Week 1 – Python for Machine Learning

Though you can just get the basics of python and directly dive into ML, I highly recommend you to take a full course on python so that you are very clear with python.

Here is a complete python course on Udemy titled “Complete Python Bootcamp: Go from zero to hero in Python 3“.

It is a pretty good course on Python and will surely give you good python skills.

Python Course on Udemy

Week 2, 3, 4 – Machine Learning and Data Science

After completing python and required math you are ready to dive into ML.

So, here is a course on Udemy titled “Machine Learning, Data Science and Deep Learning with Python“. This course covers various concepts of ML and Data Science and their implementation in Python.

Give all your remaining weeks in month 2 to this as you need to understand this for sure. At the end of this week you have a project which will give you some hands on experience.

Machine Learning course on Udemy

If you are done with that course and the project and
1. If you want to understand the algorithms at their core, i would recommend a ML course by Andrew Ng on Coursera titled “Machine Learning
2. If you want to do more projects without any guidance, here is an awesome list.

Month 3 – Guided Projects

After these two months of learning and hard work I hope that you are now very good at the concepts and implementation (Keep practicing them so that you do not forget them). So, this month we are gonna do 6 guided projects which are real world problems being solved by ML.

You can add these projects in your CV and showcase them to get jobs in ML. If you buy all the courses you will be also getting a lot of certificates which you can showcase in your CV.

For this, you need to take a course on Udemy titled “Machine Learning Practical: 6 Real-World Applications“. This is a detailed course where in you will learn the step by step process of developing a ML project.

Machine Learning projects on Udemy

After doing these projects try to do some more projects from this list

Disclaimer: All the Udemy courses which I mentioned are price around 10$ for most part of the year but sometimes its priced higher, if it is priced higher when you see, do not buy it.

Unofficial Thing: You can find free download links for these Udemy courses on some sites. Just search for it


Congo guys, you are now very good at ML, ML concepts and ML projects. After doing some projects on your own, you will be ready to get into the industry of Machine Learning.

I hope you like this article guys, if yes do share it with your friends who want to get into the field of Machine Learning. Do comment your opinion or anything you want to convey to me.

Sharing is caring!

Leave A Reply