Module 2: Machine Learning Basics

Welcome back! In this module, Maria Chen will teach you how AI actually learns from data. You'll discover features, labels, training data, and the different ways machines learn.

What You'll Learn:

  • 📊 How machines learn from examples (not rules)
  • 🔍 Features - what AI looks at to make decisions
  • 🏷️ Labels - the correct answers for training
  • 🎯 Three types of learning: supervised, unsupervised, reinforcement

Where Does Machine Learning Fit?

Before diving in, let's see the big picture. Click each layer to learn what it is and why it matters.

🤖 Artificial Intelligence — any system showing intelligent behavior
📊 Machine Learning ← this module
🧠 Deep Learning — Modules 3-4
Transformers / LLMs — Module 5

Click each layer to explore (0/4 explored)

Core ML Concepts

Now let's explore the building blocks of Machine Learning. Click each card to learn more.

📖
Teaching by Example
Click to learn more
📊
Training Data
Click to learn more
🔍
Features
Click to learn more
🏷️
Labels
Click to learn more

Click each concept (0/4 explored)

Feature Selection Challenge

You're building an AI spam detector! Which features would help the AI identify spam emails?

Scroll down to continue
📧 Your Mission: Build a Spam Detector

Select the features that would actually help identify spam emails. Not all features are useful - choose wisely!

Instructions: Click on features you think are good indicators of spam. Find all 5 useful features to continue.

Find all 5 useful features (0/5 found)

Supervised Learning

The most common type of ML! The AI learns from examples that have correct answers (labels) attached.

Scroll down to explore
🎯
Key Concept: In supervised learning, every training example comes with the correct answer. It's like learning with a teacher who tells you when you're right or wrong!

Real-World Examples

Click each card to explore how supervised learning is used.

📧
Email Spam Detection
Click to learn more
🖼️
Image Classification
Click to learn more
🏠
Price Prediction
Click to learn more

Click each example to learn about it (0/3 explored)

Unsupervised Learning

Here the AI finds patterns on its own - without being told the right answers!

Scroll down to explore
🔍
Key Concept: In unsupervised learning, there are no labels or correct answers. The AI explores the data and discovers patterns, groups, or anomalies on its own!

Real-World Examples

Click each card to explore how unsupervised learning is used.

👥
Customer Grouping
Click to learn more
⚠️
Anomaly Detection
Click to learn more
📰
Topic Discovery
Click to learn more

Click each example to learn about it (0/3 explored)

Reinforcement Learning

Here the AI learns by trial and error — making decisions and getting feedback!

Scroll down to explore
🎮
Key Concept: In reinforcement learning, the AI (called an "agent") independently makes decisions and takes actions in an environment to achieve a goal set by humans. It receives rewards for good decisions and penalties for bad ones. Over time, it learns which actions lead to the best outcomes — just like learning a video game!

Real-World Examples

Click each card to explore how reinforcement learning is used.

♟️
Game-Playing AI
Click to learn more
🤖
Robot Navigation
Click to learn more
💬
Chatbot Training (RLHF)
Click to learn more

Click each example to learn about it (0/3 explored)

ML Paradigm Sorting Challenge

Now let's test your understanding! Sort each scenario into the correct type of machine learning.

Scroll down to continue
🎯 Supervised Has labels (correct answers)
🔍 Unsupervised No labels - finds patterns
🎮 Reinforcement Trial & error with rewards

Instructions: Click a scenario, then click the correct ML type to sort it.

Scenarios
🎯 Supervised Learning
🔍 Unsupervised Learning
🎮 Reinforcement Learning

Sort all 6 scenarios (0/6 sorted)

ML Vocabulary Check

Let's make sure you know the key ML terms! Match each term to its definition.

Scroll down to continue

How to play: Click a term on the left, then click its matching definition on the right.

ML Terms
Training Data
Feature
Label
Supervised Learning
Unsupervised Learning
Definitions
The correct answer in supervised learning
Finding patterns in data without labels
The examples AI learns from
Learning from examples with known answers
An attribute used to make predictions
Match all 5 terms (0/5 matched)

Knowledge Check

Answer these questions to earn your ML Explorer Certificate!

Scroll down to see all questions
📊

ML Explorer Certificate

AI Fundamentals Series - Module 2 Complete

Bronze Level

Your Name

Has demonstrated understanding of Machine Learning fundamentals including features, labels, training data, and the three ML paradigms (supervised, unsupervised, and reinforcement learning).

Scroll down to continue

What's Next?

In Module 3: Neural Networks, you'll learn how artificial neurons work together to recognize patterns!