Skip to content

Concept Glossary: F

This page lists English glossary entries for this letter. Entry bodies are assembled from term source files.

factual claim

  • Meaning: A factual claim is a statement that should be checked against external evidence.
  • Why it matters: This concept helps readers distinguish a specific role in data, modeling, evaluation, prompting, or system operation instead of treating nearby terms as interchangeable.
  • Related concepts: interpretation, supporting evidence, prediction
  • Core Section: P1-17.3
  • Appears in: P1-17.2

factuality

  • Meaning: Factuality is the quality of whether a statement matches verifiable reality.
  • Why it matters: This concept helps readers distinguish a specific role in data, modeling, evaluation, prompting, or system operation instead of treating nearby terms as interchangeable.
  • Related concepts: supporting evidence, hallucination, model evaluation design
  • Core Section: P1-12.3
  • Appears in: P1-10.3, P1-11.1, P1-13.1, P6-10.2

false negative

  • Meaning: A false negative is an error where a case that is actually positive is predicted or ruled as negative. For example, a risky case that needs review but is treated as not needing review is a false negative.
  • Why it matters: When false negatives are costly, setting the threshold too high can miss too many risky cases. This concept separates miss cost from false-alarm cost and helps decide whether the review queue should be wider or narrower.
  • Related concepts: false positive, error cost, threshold, recall
  • Core Section: P3-9.12
  • Appears in: P3-9.12, P4-8.1

false positive

  • Meaning: A false positive is an error where a case that is actually negative is predicted or ruled as positive. For example, a case that does not need review but is sent to the review queue is a false positive.
  • Why it matters: When false positives are costly, setting the threshold too low can increase human review load or unnecessary action cost. This concept clarifies that reducing missed cases and reducing false alarms can require different operating choices.
  • Related concepts: false negative, error cost, threshold, precision
  • Core Section: P3-9.12
  • Appears in: P3-9.12, P4-6.4, P4-8.1

feature

  • Meaning: A feature is an input signal or value used by a model.
  • Why it matters: This concept helps readers distinguish a specific role in data, modeling, evaluation, prompting, or system operation instead of treating nearby terms as interchangeable.
  • Related concepts: representation, model input, parameter, feature selection, representation learning
  • Core Section: P1-4.3
  • Appears in: P1-2.3, P1-3.2, P1-3.3, P2-11.1, P2-11.2, P2-11.3, P2-12.3, P2-15.2, P3-1.1, P3-2.2, P3-3.3, P3-4.1, P3-4.2, P3-4.3, P3-5.1, P3-5.2, P3-5.3, P3-5.4, P3-5.5, P3-6.1, P3-6.2, P3-6.3, P3-6.4, P3-6.5, P3-6.6, P3-9.7, P3-summary, P5-10.1, P4-1.2, P4-3.1, P4-3.2, P4-4.2, P4-5.1, P4-7.1, P4-7.4, P4-9.1, P4-9.2, P4-10.1

feature selection

  • Meaning: Feature selection chooses which available features to keep for the current problem.
  • Why it matters: This concept helps readers distinguish a specific role in data, modeling, evaluation, prompting, or system operation instead of treating nearby terms as interchangeable.
  • Related concepts: feature, preprocessing, data leakage
  • Core Section: P4-7.1
  • Appears in: P2-12.3, P4-index, P3-6.1, P4-7.3, P4-7.4, P4-15.2, P4-3.1

fine-tuning

  • Meaning: Fine-tuning further trains a pretrained model on task or domain data.
  • Why it matters: This concept helps readers distinguish a specific role in data, modeling, evaluation, prompting, or system operation instead of treating nearby terms as interchangeable.
  • Related concepts: pretraining, in-context learning, language model
  • Core Section: P6-9.1
  • Appears in: P1-11.3, P1-12.1, P6-9.2, P6-10.3, P6-10.5

function approximation

  • Meaning: Function approximation expresses values with a function or model that estimates the value from an input, instead of storing every value directly in a table.
  • Why it matters: When the state space becomes large, storing every value in a table becomes difficult to manage, so function approximation carries the value-based intuition into larger problems.
  • Related concepts: value-based reinforcement learning, function, multilayer neural network
  • Core Section: P4-19.5
  • Appears in:

function

  • Meaning: A function maps inputs to outputs according to a rule.
  • Why it matters: This concept helps readers distinguish a specific role in data, modeling, evaluation, prompting, or system operation instead of treating nearby terms as interchangeable.
  • Related concepts: variable, model, objective function
  • Core Section: P2-2.1
  • Appears in: P2-4.2, P2-4.3, P2-6.2, P2-8.5, P2-10.3

fair use

  • Meaning: A legal doctrine that can allow limited use of copyrighted material under certain purposes and conditions.
  • Why it matters: It matters in AI learning material because reuse, quotation, transformation, and market substitution must be considered carefully rather than assumed safe.
  • Related concepts: Read together with the surrounding glossary entries and the linked Sections for this term.
  • Core Section: P1-15.2