What is Machine Learning?
Machine Learning (ML) is a subset of AI where systems learn patterns from data to make predictions or decisions without being explicitly programmed for every rule. Instead of writing rules, you provide examples and the model infers patterns.
Types of Machine Learning
- Supervised Learning: Learn mapping X → y from labeled data. Examples: regression (predict price), classification (spam vs ham).
- Unsupervised Learning: Learn structure from unlabeled data. Examples: clustering (customer segments), dimensionality reduction (PCA).
- Reinforcement Learning (RL): Agent learns via rewards/penalties by interacting with an environment (games, robotics, recommendation bandits).
AI vs ML vs Deep Learning
- AI (Artificial Intelligence): Broad field of building systems that perform tasks that normally require human intelligence.
- ML: A practical approach inside AI using data-driven learning.
- Deep Learning (DL): A subset of ML using deep neural networks (many layers) for feature learning — excels at images, speech, language.
Real-world applications
- Healthcare: disease prediction, medical image segmentation, drug discovery.
- Finance: fraud detection, algorithmic trading, credit scoring.
- Recommender systems: e-commerce, content platforms.
- NLP: chatbots, sentiment analysis, summarization.
- Computer Vision: self-driving, quality inspection.
Traditional programming vs ML approach
- Traditional: encode explicit rules → deterministic.
- ML: collect data + labels → train model that generalizes to new inputs.
- Example: rule-based spam filter vs ML spam classifier trained on labeled emails.