Getting Started → Orientation
Orientation ~5 min

Start Here: Your Guided Path Through the AI Course

Welcome! This page will guide you through the course structure, help you assess your readiness, and set you up for success in learning the foundations of artificial intelligence.

Before You Begin

This course is designed to be rigorous and comprehensive. To get the most out of it, you should complete the prerequisites first. Think of them as the foundation—without them, the main course modules won't make sense.

📚 What You Need to Know First

Mathematics Prerequisites:
  • Functions: What f(x) means, how to read graphs
  • Vectors: Arrays of numbers, geometric interpretation
  • Dot product: How to compute it, what it represents
  • Derivatives: Rate of change, slopes of curves
  • Basic probability: P(A), conditional probability
Programming Prerequisites (Optional but Helpful):
  • Variables: Storing and naming data
  • Loops: Repeating actions (for, while)
  • Conditionals: if/else logic
  • Functions: Defining reusable code blocks

Not sure? Check the Prerequisites section on the homepage for detailed guides and self-assessment questions.

Recommended Course Order

Follow this sequence for the best learning experience. Each step builds on the previous ones.

Phase 1: Prerequisites (Complete These First)

Mathematics

  1. Math Foundations — Functions, variables, graphs
  2. Number Sense — Real numbers, growth patterns
  3. Logic Basics — Propositions, truth tables
  4. Calculus — Derivatives, chain rule
  5. Linear Algebra — Vectors, matrices, dot products
  6. Probability — Basic probability, expectation

Programming (Optional)

  1. Programming Foundations — What is a program?
  2. Python Basics — Variables, data types
  3. Control Flow — Loops, conditionals
  4. Functions & Data — Functions, lists, dictionaries

Phase 2: Main Course (In Order)

  1. Module 1: Foundations — What AI Is, Pattern-Finding, Probability, Optimization
  2. Module 2: Core Methods — Decision Boundaries, Neural Networks, Backpropagation, Regularization
  3. Module 3: Modern Architectures — Embeddings, Attention, Transformers, LLMs
  4. Module 4: Generative AI — Generative Models, Diffusion, Multimodal Systems
  5. Module 5: Evaluation & Practice — Model Evaluation, Responsible AI, Deployment

Don't skip ahead! Each module assumes you've mastered the previous ones.

How Long Will This Take?

Prerequisites

6–10 hours

Mathematics + Programming basics

Main Course

12–18 hours

All 19 modules with labs

Total Time

18–28 hours

Complete course from start to finish

💡 Pacing Recommendations

  • Intensive pace: 1–2 weeks (3–4 hours/day)
  • Moderate pace: 3–4 weeks (1–2 hours/day)
  • Relaxed pace: 6–8 weeks (30–60 min/day)

Quality over speed. It's better to deeply understand Module 1 than to rush through all 19 modules superficially.

How Each Module Works

Every module follows a carefully designed learning flow to build understanding progressively:

1

Intuition First

We start with real-world analogies and visual explanations. Why does this concept matter? What problem does it solve?

2

Mathematical Depth

Then we dive into the math. Equations, formulas, proofs. This is where you understand how it works.

3

Interactive Lab

Play with the concept! Interactive visualizations let you adjust parameters and see results in real-time.

4

Code View (Optional)

See production-quality Python/PyTorch implementations. You can read, copy, or modify the code.

5

Recap & Quiz

Key takeaways and self-check questions verify your understanding before moving forward.

Final Advice: How to Succeed

◈

You Don't Need to Understand Everything Immediately

AI is complex. Neural networks, backpropagation, attention mechanisms—these aren't simple topics. Confusion is normal and expected. The first time you read about gradient descent, it might not click. That's okay. Read it again. Try the lab. Look at the visualizations. Understanding comes with repetition and practice.

✨ Tips for Success

  • Take notes by hand. Writing forces you to process, not just consume.
  • Do the math yourself. Don't just read the equations—work through them on paper.
  • Ask "why?" constantly. Why this formula? Why this architecture? Curiosity drives understanding.
  • Revisit modules. Come back to Module 1 after Module 5. You'll understand it differently.
  • Explore the labs. They're interactive for a reason. Change the parameters. Break things. Learn by doing.
  • Don't compare your pace. Some people fly through; others take it slow. Both are fine.

🚀 Ready to Begin?

Start with the prerequisites if you haven't already, or jump straight into Module 1.1: What AI Actually Is if you're confident in your background.

Remember: The goal isn't to finish quickly. The goal is to deeply understand how AI works.