# How an AI Learns
There are several forms an AI can learn
| Method | Explanation | Example | |
|---|---|---|---|
| Supervised Learning | Learning with labeled data; predicting outcomes based on known examples (e.g., image classification, spam detection). | Image classification | |
| Unsupervised Learning | Learning without labeled data; finding patterns and structure in data (e.g., clustering, dimensionality reduction). | Recommendation System | |
| Reinforcement Learning | Learning through rewarding feedback | Roboter | |
| Generative Ai | Learning through statistics - finds data | ChatGPT |
# Breakdown
# Supervised-Learning
while creating this ML model - there is a supervision training & feedback
several phases
- training phase - feed the ml-system with data
- model is trained with data
- learning takes place through
epochs(learns a bit ⇒ feedback ⇒ improves for next time)
# Example
Dad teaches child how to swim in pool. The child learns to swim gradually after many sessions based on regular feedback from his dad.
# Unsupervised-Learning
no supervision for this ML model
facts
- no trainings
- model is fed with data - has to learn & find patterns/realtionships by itself
# Example
There is no dad to supervise here. The child simply jumps into the pool and has to learn swimming on its own.
# Supervised- vs Unsupervised- Learning
Supervised model
- data has output label
- learns mapping between input & output
- based on feedback
Unsupervised Training
- data has no output label
- model learns pattern/relationship without any feedback
# Example
# Sub-Categories
Supervised Learning
2 main subcategories
- Regression
- Classification
Unsupervised Learning
3 main subcategories
- Clustering
- Association Rule Mining
- Dimension Reduction
# Breakdown
