ml-mitchell-1997-formal-definition

IN premise — entries/2026/06/21/wiki-Machine_learning-chunk-7.md

Created 2026-06-21T09:55:51+00:00

Tom Mitchell's (1997) formal definition: a computer program learns from experience E with respect to task T and performance measure P if its performance on T as measured by P improves with experience E

Dependents

These beliefs depend on this one:

• IN formal-learning-definition-contains-seeds-of-crisis — Mitchell's formal definition of learning — improvement on task T via experience E measured by performance P — relies on a performance measure P that functions as a proxy. Since standard evaluation methodologies and overfitting defenses address training-test generalization but are not designed to detect deployment-specific failure modes such as adversarial vulnerability and algorithmic bias, the definition's reliance on P may leave a structural gap between what the formalism measures and what deployment requires — suggesting that some of ML's deployment challenges are connected to limitations already present in the foundational framing, not solely to particular methodological shortcomings.
• IN ml-foundationally-bounded-and-task-relative — ML is foundationally bounded to task-relative operation — Mitchell's definition structurally requires domain-specific choices (task T, experience E, measure P) and the No Free Lunch theorem mathematically proves no universal escape exists, jointly establishing task-relativity as an invariant of the field, not a limitation to overcome.