Skip to content

Concept Glossary: B

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

backpropagation

  • Meaning: Backpropagation is the procedure that computes how much the loss at the output depends on each parameter by working backward through the network. More precisely, it applies the chain rule along the computation graph to distribute the final error signal across intermediate activations and weights.
  • Why it matters: A neural network cannot reduce loss unless it knows which direction each weight should move. Backpropagation provides that gradient signal efficiently, so learning becomes a concrete calculation rather than a vague idea that the network adjusts itself. It also explains why deep layers can be trained by tracing each connection's contribution to the final error.
  • Related concepts: gradient, loss function, chain rule
  • Core Section: P5-5.1
  • Appears in: P5-5.2, P5-6.1, P5-7.1

baseline

  • Meaning: A baseline is a reference point used to read change or difference by comparing the current value with a normal range or another target. It keeps a number from being interpreted by itself and asks what it changed against.
  • Why it matters: A recent value or model score is hard to interpret alone. A baseline gives comparison reports and operational data a stable point of reference, so readers ask how much something improved, worsened, or moved from the expected pattern instead of overreading an isolated number.
  • Related concepts: comparability, modeling output structure, baseline model, model evaluation design
  • Core Section: P3-7.3
  • Appears in: P3-1.1, P4-index, P3-1.2, P3-2.2, P3-3.2, P3-3.3, P3-4.1, P3-4.2, P3-4.3, P3-5.1, P3-5.2, P3-5.3, P3-6.5, P3-6.6, P3-7.1, P3-7.4, P3-7.5, P3-8.1, P3-8.2, P3-8.3, P3-8.4, P3-8.5, P3-9.1, P3-9.3, P3-summary, P4-6.1, P4-6.2, P4-8.2, P7-index, P7-1.1, P7-1.3, P7-2.2, P7-7.3, P7-summary

baseline model

  • Meaning: A baseline model is the simplest comparison model or score used to check whether a more complex model has made a meaningful improvement. It gives the project an interpretable starting point before adding more complexity.
  • Why it matters: A high score can come from an easy task rather than a better modeling method. A baseline model fixes the minimum comparison point that candidate models must beat, and it makes error examples and execution summaries more useful because readers can see what changed beyond the simplest approach.
  • Related concepts: model evaluation design, baseline, model selection, task definition
  • Core Section: P4-8.2
  • Appears in: P3-7.1, P4-index, P4-3.1, P4-3.2, P4-4.2, P4-6.1, P4-6.2, P4-8.1, P4-8.3, P4-9.1, P4-10.1, P4-12.1, P4-13.1, P4-15.1, P4-16.1, P4-summary, P7-index, P7-2.1, P7-4.2, P7-summary

bootstrap

  • Meaning: A resampling method that creates new sample sets by drawing from the original data with replacement.
  • Why it matters: Bootstrap samples make it possible to see how much a model or estimate changes under slightly different samples from the same data. In random forest, each tree sees a different bootstrap sample, which creates diversity among trees.
  • Related concepts: random forest, ensemble, OOB score, sample
  • Core Section: P4-15.1
  • Appears in: P4-15.3, P4-15.4

business decision

  • Meaning: A business decision is the stage where an AI system's model score, rules, costs, risks, policies, and possible human review are combined to decide an actual operational action. The fact that a model produced a number and the act of deciding what to do with that number must be kept separate.
  • Why it matters: A probabilistic output is only decision material, not the final business decision itself. This distinction helps separate actions such as automatic processing, deferral, follow-up questions, and human review from the model output, and it also makes decision responsibility easier to locate.
  • Related concepts: probability estimate, threshold, human oversight
  • Core Section: P1-6.3

bias

  • Meaning: Bias is the problem where an AI system repeatedly produces more harmful, unfavorable, or distorted results for certain people, groups, or situations. It is not just a single wrong prediction; it asks who receives failures more often and in what direction.
  • Why it matters: Bias can arise from data collection, labeling standards, feature choices, evaluation methods, and deployment context, even without bad intent. A model can look strong on average while still creating concentrated harm, so group-level error patterns and operating context must be examined separately.
  • Related concepts: safety, accountability, human oversight
  • Core Section: P1-15.1
  • Appears in: P3-8.6

broadcasting

  • Meaning: Broadcasting is an array computation rule that lets a compatible smaller array or scalar be applied across a larger array. It is better understood as a shape interpretation rule than as manually copying values into a huge array.
  • Why it matters: Broadcasting explains how short array expressions can apply values along particular axes without explicit loops. It helps readers debug cases where an operation works syntactically but spreads values along a different axis than expected.
  • Related concepts: vectorization, tensor, scalar
  • Core Section: P2-11.3
  • Appears in: P2-11.4, P2-12.1

Bayes' rule

  • Meaning: A probability rule for updating a belief about a hypothesis after observing new evidence.
  • Why it matters: It provides the basic structure for reading how prior belief, evidence likelihood, and updated probability relate.
  • Related concepts: Read together with the surrounding glossary entries and the linked Sections for this term.
  • Core Section: P2-5.1