Hey — Steve here.

Last week we covered Model. This week, let's talk about something you've probably heard but maybe never fully understood.

This Week's Term: Machine Learning

The quick version: Instead of programming every rule by hand, you show the computer thousands of examples and let it figure out the pattern. Like learning to cook by tasting, not reading recipes.

The deeper version:

Imagine you're teaching a kid to recognize dogs. You don't sit them down and say, "A dog has four legs, fur, a tail, weighs between 5 and 150 pounds..." You just point at dogs. "Dog. Dog. Not a dog. Dog." After enough examples, the kid gets it. They can spot a dog they've never seen before.

Machine learning works the same way. Instead of a programmer writing every single rule ("if this, then that"), you feed the computer thousands — or millions — of examples, and it figures out the patterns on its own. Show it 10,000 spam emails and 10,000 real emails, and it learns what spam looks like. Show it a million photos of cats and dogs, and it learns to tell them apart.

The "learning" part is real. The system actually gets better with more data. That's what makes it different from regular programming, where a program only does exactly what you told it to do. A machine learning model can surprise you — for better or worse.

Why This Matters

Because machine learning is already running your life. It decides what shows up in your social media feed, what Netflix recommends, whether your email goes to spam, whether your loan gets approved, and increasingly, whether you get that job interview. Understanding the basics helps you understand why these systems sometimes get things hilariously wrong.

Try It Yourself (2 minutes)

Open your email spam folder. Every email there was filtered by machine learning. The AI learned from millions of examples what spam looks like.

Go Deeper

• Search for "Machine Learning explained simply" — you'll find great visual guides
• 🔗 Read the full SpeakNerd term page

The Nerd Corner

Machine learning is a subset of AI where algorithms build mathematical models from training data to make predictions or decisions without being explicitly programmed for each scenario. Major paradigms include supervised learning (labeled data), unsupervised learning (finding hidden patterns), and reinforcement learning (trial and error with rewards). Common algorithms include linear regression, decision trees, SVMs, and neural networks.

Next week: Deep Learning — we'll break down what it means and why you should care.

— Steve

P.S. Know someone who'd find this useful? Forward this email. They can sign up here.