Machine Learning Roadmap

This is complete end to end machine learning roadmap, whether you are a beginner or a expert in machine learning, this is comprehensive roadmap for one to ace in machine learning.

If you are a beginner then first you need to identify which type of beginner you are, there are quite a different type of beginners as follows:

  1. Who knows is new to programming and have no prior experience in that.
  2.  Who knows little bit of programming like what are loops/case/if-else, done in high school but needs to revise concepts before starting
  3. Who are in currently studying computer science in engineering or in bachelors, but they want to start with machine learning.
  4. Who knows good mathematics but new to programming and machine learning

we will look into each of them and from where one should start to learn machine learning. 

starting from 1st one, the one who is new to programming, don’t know anything about it, is a absolute beginner, these kind of people should start from learning python or any other programming language like c++, c, java, but python is preferred for machine learning as it has very good community support in terms of tools available to implement machine learning. one can learn python from:

  1. Codecademy
  2. Google Python Class
  3. Python 3 Programming Specialization

Some good books to learn python are:

  1. Learn Python the Hard Way: 3rd Edition
  2. Python cookbook: Recipes for Mastering Python (3rd Edition)
  3. Python Crash Course 

After going through how python works, basic, constructs, we recommend to do some problem solving using python. There are alot of good platforms for that. some of them are listed below:

  1. Introduction to Python
  2. Leetcode Problem sets

Now comes the 2nd type of people who know what is python how it works but don’t know a great deal about programming.  

They can directly jump into Problem solving using python on Leetcode or Hackerrank to brush up their concepts.

This same guide of practicing python for problem solving would be recommended to 3rd type of candidates and for 4th type of candidates, they can follow guide for 1st type of candidates. 

Now you know how to code in python, write loops, if-else and basic constructs. 

To learn machine learning and data science you need to learn some specific libraries in python where each library has its own importance in the field of machine learning. They are as follows:

  1. Numpy: used for optimised numerical computations in python.
  2. Pandas: used for data handling and data manipulation.
  3. Matplotlib: used for data visualization
  4. Seaborn: used for data visualization in extension with matplotlib to create enhanced visualizations.
Now the question is from where one can learn all these so here are the resources for each of them:
For Numpy:
  1. cs231n: Python Numpy Tutorial
  2. Learn Numpy
  3. Introduction to Numpy
For Pandas:

For Matplotlib:

  1. Introduction to Matplotlib
  2. Python Plotting with Matplotlib
  3. Matplotlib

For Seaborn:

  1. Seaborn Tutorial for Beginners
  2. Python Seaborn Tutorial For Beginners
  3. Official Seaborn Docs
At this time you know python, already solved bunch of question in problem solving with python, you also know about basic python libraries to use. 
Now this is the time to learn about mathematics, you had already learned mathematics at high school or at graduation but we recommend to revise all the concepts again before starting with machine learning, and the main difference between the mathematics required to solve machine learning problems and what we study at school is, here in machine learning we need applied mathematics, we need to apply theorems and concepts to solve real world problem whereas in school we only solve questions based on theorems and equations, but here we need to make equations and then solve them. There is a thin gap between what mathematics you have learned and what is required to solve machine learning problems. 
Let’s look at some of the concepts we need to learn before starting machine learning.
  1. Probability and Statistics
  2. Linear Algebra
  3. Calculus
  4. Number Theory
  5. Convex Optimization
Here are the resources for each one of them:
For Probability and Statistics:

Close Menu