Skip to main content
Back to module
Lesson 2 of 3

Types of Machine Learning

The Five Types

1. Supervised Learning (Learning with a Teacher)

  • Teacher provides: Question + Answer
  • AI learns the pattern between them
  • Uses: Spam filters, medical diagnosis, price prediction

2. Unsupervised Learning (Learning by Discovery)

  • No teacher! Just raw data
  • AI finds hidden patterns and groups
  • Uses: Customer segmentation, recommendation systems

3. Reinforcement Learning (Learning by Trial & Error)

  • AI takes action → Gets reward or penalty → Adjusts
  • Uses: Game playing, robotics, self-driving cars

4. Semi-Supervised Learning (The Budget Option)

  • Small amount of labeled data + large amount of unlabeled data
  • Result: Good performance with 90% less labeling cost

5. Transfer Learning (Learning from Experience)

  • AI learns Task A → Uses that knowledge for Task B
  • Example: AI trained on 10 million general photos, then fine-tuned on 1,000 teff disease photos → Excellent teff detector!
Exercise10 points0 attempts

A spam filter that learns from emails you've marked as 'spam' or 'not spam' is an example of which type of Machine Learning?

Exercise10 points0 attempts

An AI that learns to play chess by playing millions of games and getting points for winning and losing points for losing is using: