Concept Glossary: N¶

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

n-gram¶

Meaning: An n-gram is a contiguous group of n words, characters, or tokens used as a short local context unit.
Why it matters: It shows how earlier language models counted short nearby fragments before modern models handled richer and longer context.
Related concepts: language model, statistical language model, sparsity
Core Section: P1-11.1
Appears in: P1-9.3, P6-19.1

Meaning: An ndarray is NumPy's core multidimensional array structure for efficient numeric computation.
Why it matters: It separates Python lists from calculation-oriented arrays with shape, dtype, ndim, indexing, and broadcasting behavior.
Related concepts: NumPy, shape, dtype
Core Section: P2-11.1
Appears in: P2-11.2, P2-11.4, P2-12.1

Meaning: ndim is the number of dimensions, or axes, in a NumPy array.
Why it matters: It helps readers check array structure before reading shape operations, broadcasting, or axis-based computation.
Related concepts: shape, ndarray, dimension
Core Section: P2-11.1
Appears in: P2-11.2, P2-11.3

Meaning: A nearest neighbor is the candidate closest to a query or reference vector under a distance or similarity rule.
Why it matters: It explains retrieval and case-based reasoning by showing which existing item is used as the closest evidence.
Related concepts: similarity search, distance, top-k
Core Section: P1-13.2
Appears in: P1-13.4, P7-2.1, P7-2.2

Meaning: newaxis or np.newaxis adds a length-1 axis to a NumPy array without changing the underlying values.
Why it matters: It helps align shapes intentionally for broadcasting and prevents confusing value problems with shape problems.
Related concepts: broadcasting, shape, shared underlying object
Core Section: P2-11.4
Appears in: P2-12.1

Meaning: A next action is the immediate safe and meaningful step chosen after reading current state, observations, policy, and failure records.
Why it matters: It prevents reviews and failure notes from ending as descriptions by linking them to a concrete operational step.
Related concepts: observation, state, hold state, approval policy, retry
Core Section: P7-6.3
Appears in: P1-14.4, P7-6.1, P7-6.2

Meaning: A next question is the focused follow-up question that turns the uncertainty left by a review or comparison into the next investigation.
Why it matters: It turns comparison results and error cases into the first input for the next iteration.
Related concepts: retrospective, error case, review, improvement plan, working hypothesis
Core Section: P7-2.2
Appears in: P7-index, P7-1.1, P7-1.3, P7-2.1, P7-2.3, P7-5.3, P7-summary

Meaning: Next-output generation is the view that generated artifacts are built by extending small output pieces from the current condition and prior output.
Why it matters: It helps readers see generated text, code, and structured output as cumulative processes rather than one-shot finished objects.
Related concepts: next-token prediction, sampling, generation
Core Section: P1-10.2

Meaning: Next-token prediction computes likely next token candidates from the current context and continues generation one token at a time.
Why it matters: It is the direct basis for understanding LLM text generation and settings such as sampling, temperature, and context window.
Related concepts: token, language modeling, sampling
Core Section: P6-6.1
Appears in: P1-10.2, P5-15.1, P5-15.2, P6-5.1, P6-6.2

Meaning: A node is an individual item or point in a graph to which relationships can attach.
Why it matters: It separates what is connected from how it is connected, which is the starting point for reading graph data.
Related concepts: graph, edge, weight
Core Section: P2-9.3
Appears in: P2-9.4, P4-14.1

Meaning: Noise is variation or error in observed data that may obscure the signal relevant to the current question.
Why it matters: It keeps readers from treating every observed value as useful signal and supports input-quality diagnosis.
Related concepts: uncertainty, partial observability, error
Core Section: P1-6.1

Meaning: A non-linear structure organizes data through branching, hierarchy, or relationships rather than one straight sequence.
Why it matters: It helps distinguish sequence problems from tree or graph problems where relationships matter more than position.
Related concepts: linear structure, tree, graph
Core Section: P2-9.1
Appears in: P2-9.4

Meaning: Non-parametric memory is an external store, such as documents or retrieved records, that a model can consult without storing the knowledge in parameters.
Why it matters: It explains why RAG can update sources and trace evidence without changing model parameters.
Related concepts: parametric memory, retrieval-augmented generation, RAG, search
Core Section: P1-13.3

Meaning: Nondeterministic describes a situation where the same input or state may not lead to a single fixed result.
Why it matters: It separates multiple possible outcomes from randomness and helps interpret search, generation, and system execution.
Related concepts: random, stochastic process, uncertainty
Core Section: P1-6.2

Meaning: A notebook is a computational document that combines code, explanation, and outputs in one cell-based format.
Why it matters: It is convenient for learning and experiments, but its hidden execution state can also affect reproducibility.
Related concepts: code cell, markdown cell, reproducible record
Core Section: P2-10.1
Appears in: P2-10.2, P2-10.3

Meaning: Numerical stability means repeated computation keeps values and gradients within ranges that the machine can handle.
Why it matters: Mathematically valid formulas can fail on finite machines, so initialization, normalization, and learning rate matter operationally.
Related concepts: initialization, batch normalization, backpropagation
Core Section: P5-8.3

Meaning: NumPy is a Python library for numeric arrays and vector or matrix computation.
Why it matters: It is the bridge from ordinary Python code to array-based numeric computation used throughout AI practice.
Related concepts: array, ndarray, shape
Core Section: P2-11.1
Appears in: P2-11.2, P2-11.3, P2-11.4, P2-15.1