Skip to content
ShilpBot

Beginner track

AI Fundamentals

A plain-language introduction to artificial intelligence, machine learning and neural networks, with no advanced maths required.

Who this track is for

This track is written for anyone who keeps hearing about AI and wants a clear, honest picture of what it is and is not. It suits students choosing a career direction, professionals whose work is starting to involve AI tools, developers who want a grounded overview before diving into frameworks, and curious readers who want to separate real capabilities from hype.

What you should know first

No programming or advanced mathematics is required. If you are comfortable with percentages, averages and the idea of a graph, you have what you need. The neural network lesson mentions weights and gradients, but explains them with everyday pictures such as walking downhill in fog, so the intuition comes first and the formulas can wait until you are ready.

What you will learn

Lessons

  1. 1What Is Artificial Intelligence? A Plain-English IntroductionA beginner guide to artificial intelligence: what it means, how machine learning fits in, the main types of learning and where AI is useful and limited.7 min read · Beginner
  2. 2How Neural Networks Learn: Layers, Weights and BackpropagationA visual, jargon-light explanation of how neural networks work: neurons, weights, loss, gradient descent and backpropagation, plus the problem of overfitting.8 min read · Beginner

How to study this track

  1. Start with what artificial intelligence is and write down, in your own words, the difference between AI, machine learning and deep learning. Teaching it to a friend is a good test.
  2. Look around your day for examples of supervised learning, such as spam filters or photo tagging, and try to name the inputs and the labels each one would need.
  3. Move to the neural network lesson and focus on the four-step training loop: forward pass, loss, backpropagation and weight update. Those four steps explain most of modern deep learning.
  4. Whenever you meet a claim about AI in the news, ask three questions: what data was it trained on, how was it tested, and what happens when it is wrong. These habits matter more than any single technique.
  5. Finish by reading our article comparing AI, machine learning and deep learning, then continue to the AI for Robotics track to see these ideas applied to physical machines.

Frequently asked questions

What will I learn in AI Fundamentals?

You will learn what artificial intelligence is, how machine learning differs from deep learning, the three main ways machines learn, and how neural networks are trained.

Do I need maths to learn AI basics?

Not for the concepts covered here. Basic familiarity with averages and graphs is enough. Deeper study later uses linear algebra and calculus.

What should I study after AI Fundamentals?

Continue with the AI for Robotics track to see how perception and planning apply to real machines, or start building a small project to practise the ideas.