Free course · read lesson 1 without signing up

Inside the Transformer: GPT, Encoder, Decoder

How modern AI actually works — neural nets, attention, encoders, decoders, training and image models. With diagrams.

100% free English & हिंदी

6 lessons · ~74 min

What you will learn

Lesson 1 — read it free, no signup

This is the real first lesson, not a sample.

How does a machine "learn"? 🧠

You recognise your friend's face instantly — but could you write exact rules for it? Almost impossible. That's the problem neural networks solve. Instead of hand-written rules, we show the machine thousands of examples and let it figure out the pattern itself. A neural network is loosely inspired by brain cells: many tiny units, each doing simple maths, connected in layers. Alone each is dumb; together they spot patterns far too subtle for rules. That idea powers nearly all modern AI.

InputHidden layerOutput

Layers, weights and a bit of dialling 🎛️

Each connection between units has a "weight" — a number saying how much that signal matters. Learning is just adjusting millions of these weights. The network makes a guess, we tell it how wrong it was, and it nudges the weights a tiny bit to do better next time. Repeat millions of times and the dials settle into values that get things right. No magic, no "understanding" — just patient tuning of numbers until the output matches the examples.

💡 When people say a model "learned", they really mean millions of weight-numbers got tuned by examples. No thinking is involved. 🔧

+ 4 practice questions in this lesson, inside the app

Signup is free and only saves your progress, exam and certificate.

Free AI & job skills, in English & हिंदी.

Back to Skill the Gap