Supervised Learning: This involves training a model on labeled data, where the algorithm learns to map the input data to the correct output. It is used for tasks like classification (e.g., spam detection) and regression (e.g., predicting house prices).

Unsupervised Learning: Here, the algorithm is trained on unlabeled data and learns to find patterns and structures in the data. Clustering (e.g., grouping customers by behavior) and dimensionality reduction (e.g., feature selection) are common tasks in unsupervised learning.

Reinforcement Learning: This involves training agents to make sequences of decisions. The agent learns by interacting with an environment and receiving feedback in the form of rewards or penalties. Applications include game playing (e.g., AlphaGo) and robotics.

Deep Learning: A subset of machine learning that uses neural networks with many layers (hence “deep”). Deep learning has achieved remarkable success in tasks such as image and speech recognition, natural language processing, and autonomous driving.