Skip to content

Concept Glossary: F

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

fact

  • Meaning: A fact is a current input value or condition used as the basis for applying rules.
  • 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: rule-based system, inference engine, knowledge base
  • Core Section: P1-3.1
  • Appears in: P1-2.2, P1-15.2, P4-index, P4-summary, P4-15.3

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, working hypothesis, 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: evidence, hallucination, evaluation
  • Core Section: P1-12.3
  • Appears in: P1-10.3, P1-11.1, P1-13.1, P6-9.2

failure

  • Meaning: A failure is a state where an attempted run did not finish functionally or did not meet expected result conditions.
  • 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: hold state, run record, evaluation, retry, next action
  • Core Section: P7-6.2
  • Appears in: P1-14.6, P1-16.3, P7-6.1, P7-6.3, P7-7.2

failure type

  • Meaning: A failure type groups repeated failures by the structure of what went wrong.
  • 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: failure, evaluation, incident record, next action, project
  • Core Section: P1-16.3
  • Appears in: P7-2.3, P7-7.2

fancy indexing

  • Meaning: Fancy indexing selects values by giving a list or array of specific positions.
  • 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: boolean mask, indexing, copy
  • Core Section: P2-11.4
  • Appears in: P2-12.2

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, input, parameter, feature selection, representation learning
  • Core Section: P1-4.3
  • Appears in: P1-2.3, P1-3.2, P1-3.3, P3-1.1, P3-2.2, P3-4.1, P3-4.2, P3-5.1, P3-6.1, P3-6.2, P3-6.3, P3-6.4, P5-10.1

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: P3-6.1, P4-7.3, P4-7.4, P4-15.2

feed-forward network

  • Meaning: A feed-forward network passes inputs forward through layers without recurrent feedback.
  • 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: Transformer, self-attention, layer normalization
  • Core Section: P5-14.1
  • Appears in: P5-14.2

few-shot prompting

  • Meaning: Few-shot prompting places a few input-output examples inside the current prompt.
  • 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: example, in-context learning, prompt
  • Core Section: P1-12.2

Figure

  • Meaning: A Figure is the outer Matplotlib canvas that contains one or more plotting areas.
  • 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: Axes, plot, savefig
  • Core Section: P2-13.1
  • Appears in: P2-13.2, P2-13.3

filtering

  • Meaning: Filtering keeps only rows or values that satisfy a condition.
  • 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: aggregation, groupby, DataFrame
  • Core Section: P2-12.2
  • Appears in: P1-13.4

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, GPT
  • Core Section: P6-8.1
  • Appears in: P1-11.3, P1-12.1, P6-8.2, P6-9.3, P6-9.5

fitting

  • Meaning: Fitting adjusts a chosen model or tool to the given 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: training, inference, model
  • Core Section: P1-5.1

expert system

  • Meaning: An expert system is a rule-based AI system that encodes domain expert judgment as rules and knowledge.
  • Why it matters: This concept gives readers the vocabulary to separate roles, boundaries, and failure modes that otherwise get mixed together in AI systems and data work.
  • Related concepts: rule-based system, knowledge acquisition, inference engine
  • Core Section: P1-3.1
  • Appears in: P1-2.1, P1-2.2

fixed-length vector

  • Meaning: A fixed-length vector compresses an input into the same vector size regardless of input length.
  • 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: Encoder-Decoder, Attention, vector
  • Core Section: P1-11.2
  • Appears in: P1-9.3, P1-11.3

excessive agency

  • Meaning: Excessive agency is a state where an agent or automation system has broader action authority than the task requires.
  • Why it matters: This concept gives readers the vocabulary to separate roles, boundaries, and failure modes that otherwise get mixed together in AI systems and data work.
  • Related concepts: least privilege, scope, approval, security, agent
  • Core Section: P1-15.3
  • Appears in: P1-10.3, P1-14.6, P7-6.2

follow-up review sample

  • Meaning: A follow-up review sample is a sample marked for priority reinspection in the next iteration.
  • 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: review target, evaluation record, execution summary, error case, priority
  • Core Section: P7-3.1
  • Appears in: P7-3.2, P7-4.2, P7-summary

forecast

  • Meaning: A forecast is a supported statement about possible future change.
  • 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: scenario, indicator, prediction
  • Core Section: P1-17.1
  • Appears in: P1-17.3

derivative

  • Meaning: A derivative is the instantaneous rate of change: how much output changes when input changes by a very small amount.
  • Why it matters: Derivatives connect function behavior to optimization and learning. They prepare readers to understand gradients and why training follows directions that reduce loss.
  • Related concepts: rate of change, slope, gradient
  • Core Section: P2-4.3
  • Appears in: P2-4.4, P2-6.1, P2-6.3

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, expression, model
  • Core Section: P2-2.1
  • Appears in: P2-4.2, P2-4.3, P2-6.2, P2-8.5, P2-10.3

CNN, convolutional neural network

  • Meaning: A convolutional neural network is a neural-network structure that repeatedly reads local visual patterns and combines them into higher-level representations. Early layers can detect simple edges or textures, while later layers combine larger parts and object-level cues.
  • Why it matters: CNNs are a central example of learned hierarchical representation in image recognition. They explain why local pattern reading, convolution, and pooling became powerful alternatives to treating an image as one flat fully connected input.
  • Related concepts: image recognition, learned representation, AlexNet
  • Core Section: P1-9.1
  • Appears in: P5-11.1, P5-11.2, P5-11.3

convolution

  • Meaning: Convolution is an operation that moves a small filter across an input and computes local pattern responses at each position. It repeatedly asks whether a particular pattern appears in each local window.
  • Why it matters: Convolution is the core operation that lets CNNs read local visual patterns without mixing the whole image at once. It helps explain feature maps and why the same detector can be applied across many image locations.
  • Related concepts: CNN, convolutional neural network, pooling, feature map
  • Core Section: P5-11.2

function calling

  • Meaning: Function calling expresses which tool or function should be called with which structured arguments.
  • 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: tool use, agent, Model Context Protocol, MCP
  • Core Section: P6-13.2
  • Appears in: P6-14.1