Hello there, here is the list of topics and skills you need to learn to get started in machine learning & data science. This page is everything you need to start your ML journey. I will be adding the topics one by one as I continue to finish them. Most of the skill and project-related topics are available for free but the main topics on our website are marked premium at a reasonable price and can be purchased separately. It was done intentionally to allow users to choose a topic of their choice instead of paying a huge membership fee. However, if you are planning to learn more than one topic, consider buying bundles to save more.
All the topics are created after doing thorough research and investing no less than an average of 60 – 100 for each tutorial. This means I have covered almost everything you need to know about a particular topic. You will learn basic concepts and their application in real-world problems. Additionally, paying members can ask their doubts as well.
The problem I faced when I started learning machine learning was that I could not find a single place to learn everything. I had to navigate through different books and resources to learn one simple thing. This is the reason why I have created this platform so that you can learn a single topic from start to finish and with time every other topic related to machine learning in a similar fashion. I am trying to produce content continuously. This means at the moment of writing this, everything is not available on the site. I will try my best to add everything as soon as possible. Let’s jump in!
Table of Contents
Skills
Python – Learn Python Before You Do Anything (Free)
Before you do anything you need to learn Python or R. I recommend Python to anyone because all my posts and projects are developed in Python. Python is fundamental to machine learning so I want you to be good at it. I don’t have any courses on Python yet but I am planning to create a Python course very soon.
However, I have created one tutorial about Python but I would still recommend a different course because my tutorials are not in detail. A course on Udemy by Jose Portilla is quite nice for beginners but note that it is not everything. You will have to know more advanced concepts and practice more.
Link To My Python Tutorials: Python Tutorial – Free
Markdown (Free)
Once you know Python. Learn Markdown as it will allow you to work with Jupyter Notebooks because most of the time you will be working with Jupyter. You don’t need to pay for anything as I have already created a complete tutorial on YouTube here:
Markdown: Learn Markdown – Free
Python Libraries (Free)
Once you know Python, learn about different Python libraries. The best way to learn these is by purchasing the book Automate the Boring Stuff with Python. This book will teach you how to work with basic Python libraries. These libraries are super helpful later in your journey. Also, I have created several Python projects, please visit my GitHub repository if you want to practice these projects.
After that, you need to learn:
- Numpy For Linear Algebra – NumPy Tutorial & Notebook Tutorial – Free
- Pandas For Working With Data – Tutorial Notebook – Free
- Matplotlib and Seaborn For Graphs etc. – Notebook Tutorial – Free
One thing you should note here, you don’t need to learn everything instead be good at Python and learn how to find what is required from the documentation of these libraries. Be good at searching for what you need.
Mathematical Concepts (Premium)
Many people will tell you that you don’t need to know mathematics to get started in machine learning or data science but that’s not the case. However, while working with problems you won’t have to know a thing but still, if you want to solve and understand a problem in the best way possible you must know the mathematical concepts behind these algorithms. But at the same time, mathematical concepts and real applications are different. The problems you face in learning theory differ entirely from what you face in practice.
However, you will face a lot of problems without understanding the theory behind these black boxes. This is why I have created all the posts in a manner so that you can grasp both the mathematical and practical concepts at the same time. No matter what you do, mathematical concepts are important to learn what algorithm to use when to use and on what kind of problems. You will see your perspective will be different after you learn the fundamentals behind algorithms.
I have created detailed notes on topics that you need to know before you get started in machine learning. You can purchase my notes and ask doubts in community forums. You need to know these topics:
- Linear Algebra – Purchase The Complete Notes Here
- Probability & Statistics – Purchase The Complete Notes Here
- Advanced Calculus – Coming Soon. If you are already familiar with calculus, detailed notes if also available in one of our tutorials on SGD.
Classical Machine Learning Topics (Premium & Free) :
These are the algorithms traditionally popular before neural networks. I will cover each of them and then move towards deep learning. Learn them in sequence without missing any of them for the best result. Here I will continue to list the topics as I add them. Also don’t forget to practice problems before moving on to a new model.
- What Is Machine Learning? Understand The Important Basic Concepts Related To ML – Free
- Extra Topic: Intelligence, Knowledge, Data, Information, AGI, Superintelligence And Responsible AI – Free
- Extra Topic: AI & Jobs: Understanding How Things May Actually Happen – Free
- Singular Value Decomposition: Concepts And Applications
- Linear Regression: Concept And Application
- A Beginner’s Guide to Data Preprocessing In ML – Free
- Principal Components Analysis: Concepts And Application
- Linear Discriminant Analysis: Concepts And Application
- Naive Bayes: Concept And Application
- Logistic Regression: Concept And Application
- Support Vector Machine: Concepts And Applications
- Decision Trees: Concept And Application
- Stochastic Gradient Descent: Concept And Application
- Random Forests & Ensemble Learning: Concept And Application
- Probability Calibration in Machine Learning – Free
- Nearest Neighbors: Concept And Application
- Clustering and Outlier Detection
- Gaussian Mixture Models
Modern Machine Learning – Deep Learning Topics:
These are the deep-learning topics that you need to know:
- Optimizers For Deep Learning
- Extra Topic: Test Of Consciousness For AI – Free
- TensorFlow Simplified Guide For Beginners – Free
- Deep Learning: Introduction To Artificial Neural Networks (ANNs)
- Convolutional Neural Networks (CNNs): Concept And Application
- Advanced (Optional) – ResNet And DenseNet Implementation In Depth
- Natural Language Processing – Coming Soon
Machine Learning Projects:
- ResNet And DenseNet Implementation In Depth – Deep Learning Advanced