Feature

Designing input features to expose useful structure (e.g., ratios, lags, aggregations), often crucial outside deep le...

The internal space where learned representations live; operations here often correlate with semantics or generative f...

A parameterized mapping from inputs to outputs; includes architecture + learned parameters.

The learned numeric values of a model adjusted during training to minimize a loss function.

The field of building systems that perform tasks associated with human intelligence—perception, reasoning, language, ...

The relationship between inputs and outputs changes over time, requiring monitoring and model updates.