Glossary · B
Terms starting with B
6 of 250 glossary terms. Each entry links to its own page with why it matters and where it fits.
Definitions here are written for engineers, not grammarians: what the term means, why it matters when it comes up, and where it sits in the curriculum — most term pages name the lessons that lean on the concept, so you can jump from a definition straight to the teaching. Use the letter bar below to move through the alphabet, or press the slash key to search the whole corpus directly.
Every entry carries three things besides the definition: the plain aliases it travels under (listed as “also”), a category tag for which stretch of the curriculum it belongs to, and the cross-references that place it next to its neighbors — the terms you would meet in the same lesson. A term earns a page here only when a lesson in the curriculum actually uses it, so the corpus stays the shape of the material instead of the shape of a dictionary.
One honest way to use this page: read down the list of entries below and note every term you could not define in a sentence if a colleague asked. That list — not the whole letter — is your revision list, and each entry links to the reading that closes the gap.
BM25
Retrieval & generation
A lexical ranking function that scores a document from query-term matches while accounting for term rarity, repeated occurrences, and document length.
Backpressure
AI-native development
A flow-control mechanism that slows or rejects upstream work when a downstream component cannot process it safely at the current rate.
Backpropagation
Math & training
An efficient application of the chain rule that propagates derivatives from a scalar loss backward through a computation graph. It computes gradients; an optimizer uses those gradients to update parameters.
Batch Size
Math & training
The number of examples whose losses contribute to one gradient estimate before an optimizer update. Larger batches can improve hardware utilization and reduce gradient noise, but they require more memory and may need different learning-rate or scheduling choices.
Benchmark Contamination
Evaluation & safety
Overlap or information leakage between evaluation examples and data used to pretrain, tune, prompt, select, or otherwise improve the evaluated system.
Byte Pair Encoding (BPE)
Data & representations
A subword-tokenization method that repeatedly merges frequent adjacent units to construct a fixed vocabulary from training text.