Enabling systems to learn from data and improve their performance on specific tasks without programming.
Three main types:
- Supervised learning where the algorithm learns from labeled data, each data point having a known outcome (image classficiation, etc.)
- Unsupervised learning where the algorithm learns from unlabeled data with no outcome or label (customer segmentation, anomaly detection)
- Reinforcement learning where the algorithm learns via trial and error and receives rewards/penalties (robotics, driving)