How to start learning "Machine Learning".

How to start learning "Machine Learning".

Gaurav Pandey

Published on Jul 18, 2021

6 min read

Subscribe to my newsletter and never miss my upcoming articles

Listen to this article

Machine learning, Sounds cool right? So you want a path to Learn Machine Learning

Here's a Blog on how you should start your career as a Machine Learning Engineer or Developer! 👩‍💻👨‍💻

Before I start make sure you "follow" me for more content on Python, Software Development, Mathematics & Machine Learning

👉 If you like this Blog make sure you Like, Comment, or Share. This should be great for me.

Let's get Started ⬇

• What is Machine Learning?

👉 Before understanding the meaning of machine learning in my own way, let’s see the formal definitions of machine learning.

• Machine learning is the science of getting computers to act without being explicitly programmed.- Stanford

Here is my definition of Machine Learning.

• Machine learning is the ability of the machine to learn on its own with the Help of Algorithms and Data.


👉 Some real Facts, that most people don't know.

• You don't need too much Math to start learning ML.

• You don't need GPU or Special Hardware to start.

• It doesn't matter what's your age.

• You don't need any degree.

• You don't need too much money.

• Just follow this ⬇

Everything starts with your School Mathematics.

As I said that you don't need to be a Mathematician or get a Master's degree in Maths If, you just start to learn ML. Your school Maths is enough.

👉 I'm pretty much sure that your school teaches you these topics, if yes this should be great for you.

• Linear Algebra

• Probability

• Statistics

• Trignometry

• Arthemitic

These topics should be enough to start learning ML.


Now, The Most Important part of your ML journey. Yes, you guess right "Programming".

👉 It doesn't matter which programming language you should choose, Pick one of them.

• Python

• Java

• C++

• R

• Javascript

• Julia

But, my recommendation is "Python".

👉 So, why Python.

  • Less Code.
  • Pre-built Libraries.
  • Ease to Learn.
  • Independent of Platform.
  • Wide Community Support.
  • More Computing Power.
  • Data Generation.
  • Better and Faster Algorithm.
  • Capital Flow and Investment.

You need to focus on your Model, not on your Code.


I'm not going to mess up you with too many resources, Here is one of my favorite video courses and books.

Python for Beginners!

• Python for beginners is the perfect starting location for getting started.

• No Python experience is required!

Python for Beginners Youtube Video Course by Microsoft Developer.

More Python for Beginners!

• More Python for beginners digs deeper into Python syntax.

• You'll explore some concepts of advanced Python.

More Python for Beginners Youtube Video Course by Microsoft Developer.

Wait, Don't watch these courses like a dummy, start exploring these courses in real-world projects, It doesn't matter which project you are making.

Here is your Intermediate Python Course.

Youtube Video

👉 Here are the topics you should be focusing on.

  • Printing statements
  • Variables
  • Operators
  • Conditions
  • Functions
  • Loops
  • List slicing
  • String formatting
  • Dictionaries & Tuples
  • Exception handling
  • Data Structures
  • Accessing Web Data
  • Using Databases
  • Basic terminal commands
  • Retrieving, Processing, and Visualizing Data
  • Object-oriented programming in Python: Classes, Objects, Methods

Quick💡 tip, Most people miss "Object-Oriented Programming in Python". Here is the Youtube video which helps you to learn OOP by - Patrick Loeber

Youtube Video

👉 Congratulations! 🎉 You are somehow ready to learn more about Machine Learning.

Alright, We have a handle on Python programming and understand a bit about machine learning. Beyond Python, there are a number of open-source libraries generally used in practical machine learning.

Now, Start Exploring and Learning about Python Libraries for Machine Learning.

Such as:

• Pandas

• Numpy

• Matplotlib

• Scikit-Learn

Python Libraries for Machine Learning

👉 Pandas - For processing CSV files. Of course, you will need to process some tables, and see statistics, and this is the right tool you want to use.

Here is the best Youtube Playlist to learn Pandas for Machine Learning.


👉 Numpy - The famous numerical analysis library. It will help you do many things, from computing the median of the data distribution to processing multidimensional arrays.

Here is the best Youtube Video to learn Numpy for Machine Learning.


👉 Matplotlib - After you have the data stored in Pandas data frames, you might need some visualizations to understand more about the data. Images are still better than thousands of words.

Here is the Playlist to learn Matplotlib for Machine Learning.


👉 Scikit-Learn - This is the final boss of Machine Learning with Python. Machine Learning with Python is this guy, Scikit-Learn. All of the things you need from algorithms to improvements are here.

Here is your 3hrs Youtube Video Course. image

Start learning and Exploring the Basic of ML algorithms such as:

• Linear Regression

• K-Means

• Random Forest


• Decision Tree

They are included in Scikit-Learn Library

👉 Now, you are ready with your basic Machine Learning Skills but don't forget that you need to create real-world projects for enhancing your knowledge in this domain.

Don't forget to take a look at this course.


Foundational Machine Learning Skills.

👉 Be ready for some theory, and don’t worry about the lack of Python: this is not a course to focus on writing code.

Probably the most popular Machine Learning course in the world is


👉 You’ll cover the most important aspects of classical machine learning, including the following topics:

  • Linear and Logistic Regression
  • Regularization
  • Neural Networks
  • Support Vector Machines
  • Dimensionality Reduction
  • Anomaly Detection
  • Recommender Systems

Time to Focus on Mathematics.

The topics of math you'll have to focus on

  • Linear Algebra
  • Calculus
  • Trigonometry
  • Algebra
  • Statistics
  • Probability

The math for Machine learning e-book

👉 This is a book aimed at someone who knows quite a decent amount of high school math like trigonometry, calculus, I suggest reading this after having the fundamentals down on khan academy.


Getting to the next level, Deep Learning

👉 The Deep Learning specialization offered by DeepLearning AI is your next stop. Andrew Ng will be your teacher.


There are 5 courses on this specialization:

  • Neural Networks and Deep Learning
  • Hyperparameter Tuning, Regularization, and Optimization
  • Structuring Machine Learning Projects
  • Convolutional Neural Networks
  • Sequence Models


👉 This is a foundational program that will help you understand the capabilities, challenges, and consequences of deep learning

You’ll need Python for this one, and I’d recommend you complete the Machine Learning course before enrolling.


Building a career in machine learning is a lifelong pursuit.

But every journey starts with the first step, and I hope this thread helps you.

Now, It's time to get more into DeepLearning

Start with the TensorFlow Developer Professional Certificate offered by DeepLearning AI

👉 You’ll cover the basics of TensorFlow, and by the end of the specialization, you’ll have what you need to use the framework proficiently.


Going beyond models.

👉 DeepLearning AI released a new specialization just a couple of weeks ago. It’s called Machine Learning Engineering For Production (MLOps), and it focuses on the full machine learning pipeline.


👉 Machine learning is much more than building models, and this specialization will teach you everything you need to build end-to-end systems.

How was it? It doesn’t seem very difficult, does it? Machine Learning with Python is easy.


Everything has been laid out for you.

You can just do the magic. And bring happiness to people.

If want to add more so, Just Reply

Share this