An Interactive Machine Learning Textbook

Machine learning, explained like a story

No dry manuals here. We build intuition from first principles, support it with beautiful math, and let you play with live interactive demos.

Select Volume

Interactive Textbook PhilosophyEvery chapter is carefully written with inline simulations, allowing you to tweak parameters and observe outcomes instantly.

MLP•25 Chapters•6 hrs read

Multi-Layer Perceptron

From a single neuron to a network that learns

A story-driven, from-first-principles walk through neural networks — starting with a single artificial neuron and ending with a fully trained multi-layer perceptron, backpropagation, optimizers, and everything in between.

Table of Contents

Foundations & History

1. What Is Artificial Intelligence, Really?

Separating the hype from the actual idea

2. Machine Learning Fundamentals

Teaching computers by example instead of by rule

3. Deep Learning Fundamentals

What makes 'deep' learning different

4. A Brief History of Neural Networks

Two winters, one thaw, and a revolution

5. Biological vs. Artificial Neurons

How much of the brain analogy is actually true?

From Perceptron to MLP

6. The Perceptron

The first learning machine that could draw a line

7. Why the Perceptron Isn't Enough

The XOR problem and the first AI winter

8. The Birth of the Multi-Layer Perceptron

Stacking neurons to escape a straight line

Mathematical Foundations

9. Linear Algebra for Neural Networks

Vectors, matrices, and why networks are just matrix math

10. Calculus for Neural Networks

Derivatives, gradients, and the chain rule that makes learning possible

11. Probability & Statistics Essentials

Making sense of uncertainty in data and predictions

12. Optimization Theory

How a network actually searches for good weights

Core MLP Theory

13. MLP Architecture

Layers, neurons, and how information flows forward

14. Backpropagation

How a network learns from its own mistakes

15. Activation Functions

The spark that lets networks learn anything non-linear

16. Loss Functions

Teaching a network what 'wrong' means

17. Optimizers

Smarter ways to walk downhill

18. Weight Initialization

Why the starting point of training matters so much

19. Regularization

Keeping a network from memorizing instead of learning

20. The Training Pipeline

Putting every piece together into one training loop

Practice & Application

21. Practical Implementation

Building an MLP for real, bugs and all

22. Real-World Applications

Where MLPs actually show up in production

23. MLPs Compared to Other Architectures

When to reach for an MLP, and when not to

24. Exam & Interview Prep

The questions that come up again and again

Reference

25. Glossary

Every key term, in one place