New to Machine Learning? Start Right Here.
Introduction
This is the page we wish had existed when we started.
No assumed knowledge. No “just Google it.” A clear, opinionated sequence of what to read, in what order, and why. You’re building real understanding instead of just collecting browser tabs.
Follow this path in order. Each step builds on the last. Estimated total reading time is 4 to 6 hours. Take it one article at a time.
Phase 1 Understand the Landscape
Before you write a single line of code, you need to understand what machine learning actually is and what it isn’t. These three articles build your mental model from the ground up.
What you’ll learn:
- What machine learning actually is (and what it’s not)
- How the core process works, step by step
- The difference between supervised, unsupervised, and reinforcement learning
Reading order:
- What Is Machine Learning? (And Why Most Explanations Get It Wrong) — Start here. This article diagnoses why standard explanations fail and builds the right mental model from scratch.
- How Machine Learning Works: A Step-by-Step Breakdown — Now that you know what ML is, understand how it actually works. This article walks through the process without math.
- Supervised vs. Unsupervised vs. Reinforcement Learning: What’s Actually Different — These three categories show up everywhere. Understanding the difference is critical.
Prerequisites: None. No code, no calculus, no prior knowledge required.
Phase 2 Learn the Core Concepts
These are the ideas that show up everywhere in machine learning. Understanding them means you’ll know why things work, not just how to run them.
What you’ll learn:
- Why your models fail and how to diagnose it
- The bias-variance tradeoff and why it matters
- Feature engineering and why it’s underrated
Reading order:
- Overfitting: Why Your Model Is Lying to You — This is the concept that most beginners misunderstand. When your model works on training data but fails in production, this is why.
- Bias-Variance Tradeoff: The Concept That Explains Most ML Failures — This idea is everywhere in ML. Understanding it explains most of what goes wrong with models.
- Feature Engineering: The Skill That Separates Good ML from Great ML — Most people focus on algorithms. The real skill is in the features you create.
Prerequisites: Complete Phase 1 first.
What Comes Next?
You’ve built the foundation. The concepts are clear. What comes next depends on your goal.
If you want to keep exploring ML topics in depth, browse our Blog Hub by category. If you want a structured path to a machine learning job, check out our Career Path roadmap.
Either way, subscribe to get new concepts in your inbox every week.