Roadmap for AI & Machine Learning

Prerequisites:

• Basic understanding of Calculus, especially terms like gradient, function minimization, derivatives etc.
• Hands-on experience with Python, atleast to basic level.

General tips for entire journey:

• Important libraries and framework which will be used most of the times:

  • Keras, TensorFlow

  • PyTorch

    (You don’t have to be familiar with any of these, and will learn on the go)

• Start using Google Colab and Kaggle, as these will be used most of the time.

Topics:

Here is a list of topics, arranged in recommended order of learning:

Once you are familiar with the above topics, you will have an idea of which topic you liked most and can delve deeper into it.
Here is a list of advanced topics in more detail:

What's New (Latest Additions - LLMs, Agentic AI & Beyond):

The field has moved fast since the topics above were written. Once you're comfortable with the Machine Learning and Deep Learning basics, here is a beginner-friendly path through what's current in the industry today. You don't need to master everything below; pick what interests you and go deeper.

Once you've skimmed through these, try building small end-to-end projects (e.g. a RAG chatbot over your own notes, or a simple agent that can search the web and summarize); this is the fastest way to make the concepts stick.

Additional Resources:

1. Deep Learning Textbook
2. Pattern Recognition and Machine Learning
3. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
4. Krish Naik Machine Learning
5. Statquest
6. PyTorch Tutorials