Concept Glossary: M¶

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

machine learning¶

Meaning: Machine learning uses data or experience to improve a model for prediction, classification, generation, or judgment instead of hand-writing every rule.
Why it matters: It explains why AI moves from explicit rule writing to data-based model improvement and connects directly to generalization and evaluation.
Related concepts: model, training, parameter
Core Section: P1-3.2
Appears in: P1-1.3, P1-2.3

Meaning: A mapping connects a key or source representation to a value or target representation.
Why it matters: Mappings unify dictionaries, label conversion, ID metadata, and token-to-index relations under the same idea of correspondence.
Related concepts: dictionary, key, value
Core Section: P2-8.3
Appears in: P2-8.4, P2-9.1

Meaning: A markdown cell is a notebook cell for explanatory text, headings, lists, formulas, and interpretation rather than code execution.
Why it matters: Notebooks are computational documents, not only code runners. Markdown cells preserve intent, assumptions, and interpretation.
Related concepts: notebook, code cell, output
Core Section: P2-10.1
Appears in: P2-10.3

Meaning: Masking hides or replaces sensitive parts of information so records can remain useful without exposing the full risky value.
Why it matters: Logs and review samples need traceability, but raw secrets and sensitive values can create new risk if stored directly.
Related concepts: sensitive information, confidential information, log, security, review
Core Section: P1-15.3
Appears in: P1-14.5, P1-16.2

Meaning: A matrix is a two-dimensional arrangement of numbers organized by rows and columns.
Why it matters: Matrices are the basic shape behind table data, mini-batches, weights, and many neural-network computations.
Related concepts: vector, matrix multiplication, shape
Core Section: P2-3.1
Appears in: P2-3.3, P2-11.3

Meaning: Matrix multiplication combines rows from one matrix with columns from another to create new values or representations.
Why it matters: It is the core operation behind combining input vectors with weights to produce scores, outputs, or new representations.
Related concepts: weighted sum, matrix, linear transformation
Core Section: P2-3.3
Appears in: P2-11.1

Meaning: Mean is the central summary obtained by adding values and dividing by the number of values.
Why it matters: Many losses and summaries use a mean, but a single center value can hide spread and outliers.
Related concepts: distribution, variance, median
Core Section: P2-5.2
Appears in: P2-5.3, P2-5.4, P2-6.1

Meaning: Mean squared error averages squared differences between predictions and true values, penalizing large errors more strongly.
Why it matters: MSE connects loss functions and evaluation metrics while showing why large errors can dominate a summary.
Related concepts: error, loss function, mean
Core Section: P2-6.2
Appears in: P2-2.2, P2-15.1, P5-4.2

Meaning: Metadata is information about a document or record, such as title, date, source, permission, type, or location.
Why it matters: Search and retrieval need more than semantic similarity; freshness, permission, source, and document type also affect usability.
Related concepts: vector database, filtering, provenance
Core Section: P1-13.4
Appears in: P1-13.2, P1-14.1, P6-11.2, P6-12.1, P6-12.2

Meaning: A method is a function-like behavior attached to an object, usually called as value.method().
Why it matters: It helps readers understand object-oriented calls such as df.head(), model.fit(), and text.lower().
Related concepts: function, value, type
Core Section: P2-8.5
Appears in: P2-8.6, P2-12.2

Meaning: A metric is a numeric criterion for summarizing model performance or a type of error.
Why it matters: Model comparison depends on what the metric rewards or hides, so a high score is meaningful only after the criterion is understood.
Related concepts: evaluation, accuracy, recall
Core Section: P4-6.1
Appears in: P4-6.2, P4-6.3, P4-6.4, P4-8.2, P4-10.2, P4-15.3

Meaning: A model is a simplified computational form built for a purpose. In AI it often means a learned structure that maps input to output, but it is not the whole application or system.
Why it matters: The distinction prevents readers from confusing model behavior with system design, input design, review flow, or product quality.
Related concepts: input, output, system, application, orchestration, parameter
Core Section: P1-4.1
Appears in: P1-14.1

Meaning: Model Context Protocol is an open protocol for connecting AI applications with external tools, resources, and prompts in a common way.
Why it matters: MCP makes external capability discovery and invocation more consistent across agent and AI-app systems.
Related concepts: tool, agent, orchestration, resource, server, client
Core Section: P6-15.1
Appears in: P1-14.3, P1-14.4, P1-14.5, P6-15.2

Meaning: Model selection is the process of narrowing candidate model families by problem type, data condition, interpretability, and cost.
Why it matters: It prevents choosing algorithms by fame alone and makes the first experiment order explicit.
Related concepts: task definition, baseline, evaluation
Core Section: P4-8.1
Appears in: P4-3.2, P4-8.2, P4-9.1, P4-9.2, P4-9.3

Meaning: Multi-head attention reads token relationships through several attention heads and then combines their results.
Why it matters: Many tasks need several relationship patterns at once, and multiple heads increase the capacity to capture them.
Related concepts: self-attention, query-key-value, QKV, Transformer
Core Section: P5-13.3
Appears in: P6-4.3

Meaning: A multilayer neural network stacks multiple computation layers so intermediate representations can be transformed step by step.
Why it matters: It explains why depth means staged representation transformation, not just repeating calculations.
Related concepts: perceptron, hidden layer, activation function
Core Section: P5-2.1
Appears in: P5-2.2, P5-11.1