Supervised Learning
Supervised learning is like learning with a teacher. You're given examples with the correct answers, and you learn the pattern that connects inputs to outputs.
What Makes It "Supervised"?
The key characteristic: labeled data. Every training example includes both:
- Features (X): The input data
- Label (y): The correct answer
The model learns to map features to labels, then predicts labels for new data.
Two Types of Supervised Learning
1. Regression: Predicting Numbers
When the output is a continuous value (number on a scale).
2. Classification: Predicting Categories
When the output is a discrete category (one of several options).
Binary vs Multi-Class Classification
Common Supervised Learning Algorithms
The Supervised Learning Workflow
Regression vs Classification: Quick Comparison
| Aspect | Regression | Classification |
|---|---|---|
| Output type | Continuous numbers | Discrete categories |
| Example | Predict temperature: 72.5°F | Predict weather: Sunny/Rainy/Cloudy |
| Loss function | Mean Squared Error | Cross-Entropy |
| Evaluation | MAE, RMSE, R² | Accuracy, Precision, Recall |
Key Takeaways
- Supervised learning uses labeled data (inputs + correct outputs)
- Regression predicts continuous values (numbers)
- Classification predicts discrete categories
- The workflow: collect data → split → train → evaluate → predict
- This is the most common type of ML in industry
Next, we'll explore unsupervised learning - where machines find patterns without labeled answers!
اختبار قصير
التالي · الدرس 6 من 35
Unsupervised Learning
قراءة 2 دقيقة
أنهيت 5 من 35 درسًا

اسأل Byte عن هذا الدرس
محادثة خاصة حول هذا الدرس. قرأ Byte الدرس كاملًا، ويجيب خلال ثوانٍ، ويُظهر القسم الذي تأتي منه كل إجابة. يمكنك السؤال بأي لغة.
الأسئلة والأجوبة
أسئلة عامة حول هذا الدرس. يجيب AI Tutor فورًا بلغتك، ويراجع فريق FreeAcademy الإجابات، ويمكن لكل المتعلمين قراءتها.

