The workhorse algorithms of applied ML — ranked by practical usage.

Neural architectures that learn hierarchical representations from large datasets.

Group unlabeled data by structure and similarity to discover segments.

Compress and visualize high-dimensional data while preserving structure.

Match users to items they're most likely to engage with.

Flag rare, suspicious, or faulty observations that deviate from the norm.

Predict future values from trends, seasonality, and lagged signals.

Learn decision-making policies by maximizing reward.

Extract meaning, structure, and signals from natural-language text.

Classify, detect, segment, and generate visual content.

Learn from data defined over nodes and edges.