predictive coding

Predictive coding is a theory in neuroscience proposing that the brain constantly generates predictions about incoming sensory information, then updates its models based on prediction errors—the differences between what was expected and what actually arrives.

The framework suggests perception is not passive reception but active inference: Predictive coding explains why we often see what we expect to see.

In legal contexts, predictive coding refers to machine learning software that classifies documents during discovery, trained on human reviewers' decisions to identify relevant materials.