Machine Learning is a part of Artificial Intelligence.
It allows computers to learn from data on their own.
No need to program every rule manually.
It uses algorithms to find patterns in data.
More data = better learning and better predictions.
It helps computers make decisions or predictions.
Works similar to how humans learn from experience.
Uses algorithms to analyze and understand data.
Supervised Learning
Supervised learning is a machine learning technique.
It uses labeled data (input + correct output).
Training dataset contains input–output pairs.
Model learns the relationship between input and output.
Goal: Predict correct output for new unseen data.
Model compares predicted output vs actual output.
Error measured using a loss function.
Model updates parameters to reduce error.
Unsupervised Learning
Unsupervised learning is a machine learning technique.
It uses unlabeled data (no correct answers given).
Model finds patterns & relationships on its own.
Helps in grouping & organizing data.
Mainly used for clustering (grouping similar items).
Also used for dimensionality reduction (simplifying data).
Model discovers hidden structure in data.
Reinforcement learning
Reinforcement learning is a machine learning technique.
Model is called an agent.
Agent learns by interacting with an environment.
No labeled data — it learns by trial and error.
Agent receives rewards for correct actions.
Gets penalties for wrong actions.
Goal: maximize total reward over time.