Machine Learning Flavours
3 Flavours:
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Supervised Learning - “learning with a teacher”
You give the computer examples with the correct answers. It learns the connection between the input and the output.
Example: Show photos with labels “cat” or “dog”, so it learns to tell them apart.
Common uses: spam email detection, predicting house prices.
Unsupervised Learning - “learning without a teacher”
You give the computer data without answers. It tries to find hidden patterns or groupings on its own.
Example: Give it customer shopping data, and it groups customers with similar buying habits.
Common uses: Market segmentation, finding patterns in medical data.
Reinforcement Learning - “learning by trial and error”
The computer tries something, gets feedback, and learns what works best over time.
Example: A robot tries walking, falls, adjusts, and eventually learns to walk steadily.
Common uses: Game-playing AI, self-driving cars.
Summary
Supervised: learn from correct answers
Unsupervised: find patterns without answers
Reinforcement: learn by trial and error