How to get started to Machine Learning?

Hey there 👋 Hope you are doing well 😊
As you know AI wave is all over everyone is trying different AI based services and getting amazing results. Every platform out there is embedding AI to make their platform more smart and useful. AI is one of the most important skills of this decade. But getting started to it is really difficult and can be misleading sometimes. So it is very important to follow right path to understand AI better. Getting into AI means getting started with Machine Learning. In this article I am going to tell you about how you can start your journey to Machine Learning and become master in it.

Get Started with Python

To go into Machine Learning you should know Python first. Learn basics first like how variables are created and manipulated, how loops and conditions work, how functions are formed and used, how lists, arrays, maps etc. created and work. Then you should learn about OOPs in Python. And finally you should know all about Pandas and Numpy libraries as these are going to be very useful in the journey of Data Science.

Learn Maths

While learning Python, you should also devote your time in studying Maths as this subject is like a backbone of Machine Learning, Deep Learning, NLP etc. You should be familiar with Statistics, Linear Algebra, Probability theory, Hypothesis Testing, Calculus and Optimization. If you know these topics very well (clarity in basics) then you will find ML algorithms very easy. Also don't forget to implement Maths functions using Python.

Study EDA and Feature Engineering

Now it is time to play with data😈. EDA stands for Exploratory Data Analysis this gives important insights from your dataset. It is very important for knowing relationship between different features in your dataset. Feature Engineering involves manipulating features in your dataset in order to make your data more resourceful. This complete process involves knowing about data and handling it efficiently. The libraries you should know are Seaborn, Matplotlib, Missingno, PyOd.

Machine Algorithms

This is the part which you have been waiting for. Start studying about Machine learning algorithms now. Study all supervised and unsupervised learning algorithms. Get the maths and geometrical intuition implement them from scratch then understand the pre defined libraries. You should know about sklearn and its sub libraries here.

Improvise Model

Now you know about Machine Learning Algorithms, now it is time to know about the techniques used to improvise them. Learn Cross-validation techniques, HyperParameter Tuning techniques and Ensembeling methods. Get into details and practice them on datasets.

Auto ML

As you have came a long way now it is time to automate your tasks. Study Auto ML and practice get to know about Pipelines, Optuna etc.

Know about Version Controls

Learn to use Git so that you can automate the process of deployment and management.

And the learning path goes on....
If you really want to master it then practice is very important. You can practice ML on different platforms.

Important Platforms

• Kaggle -: This is one of the most famous platforms for datascience. They hosts competitions. They have variety of datasets and tutorials and large community.
  Link -: https://www.kaggle.com/

• Jupytor -: This is an IDE for creating Data Science projects. You can use Google Notebooks too.
  Link -: https://jupyter.org/

• Github -: This is one of most famous platforms. It has got enormous datasets from where you can practice and make contributions on different projects.
  Link -: https://github.com/

Important Resources

• Maths -: Statquest statistics playlist on YouTube
  link -: https://youtu.be/qBigTkBLU6g?si=tn5f8dBQo_-xDfqr

• Machine Learning -: CampusX playlist (Hindi), Coursera Andrew Ng ML specialization course.
  CampusX
  Link -: https://youtu.be/ZftI2fEz0Fw?si=VrfnThcAc8z0OQ2N
  Coursera
  Link -: https://www.coursera.org/

So this was the complete roadmap for Machine Learning.
Thankyou 💚