Model capacity is a human-made measure of a machine-learning model's representational capability — the range and complexity of functions it can approximate given its architecture and parameters. Parameters: (1) parameter count (total trainable weights and biases), (2) architectural constraints (layer depth, width, connectivity pattern, activation functions), (3) effective capacity (parameter-adjusted by regularization strength, data constraints, and optimization dynamics). Persistence mechanism: specification sheets in model documentation, benchmark reporting protocols, and the reproducible training pipelines of the machine learning research community. [formal capacitatis modeli | substrate: mind | horizon: a training run | explicit: yes | epoch: 0.03]
Accepted ontology entry
model capacity
Model capacity is a human-made measure of a machine-learning model's representational capability — the range and complexity of functions it can approximate given its architecture and parameters. Parameters: (1) parameter count (total train…
Definition
Why it is in scope
model capacity is a human-made concept in machine learning and statistics describing the ability of a model class to approximate complex functions — defined by its structural parameters, architecture, and representation power, and persisting through formal analysis in learning theory and practical calibration during training
Names and aliases
- model capacityen · CANONICAL
Relations from this entry
- cmrxj3acr03cmsoacx73fal1oDERIVED_FROM →
Test: which came first? Statistics as a field (centuries old) predates the formal concept of model capacity in machine learning (1990s). The concept of model capacity grew out of statistical learning theory and the bias-variance decomposition.
- cmrwiv1rn00a8soacg5vdpiogINSTANCE_OF →
which-kind test: model capacity is a specific kind of metric — it measures the representational complexity a model class can achieve. Direction specific→general is correct. A competent speaker calls capacity 'a metric.'
Relations to this entry
No accepted relations in this direction.
Record identity
- Created
- Aug 8, 2026, 9:15 PM UTC
- Content hash
- efcdb56c053759e0a665943fe309fbd2dd42e0bf2782fb6722608b5838239a9e