Skip to content

Class: NeuralNetworkModel

AIModel realised as a neural network (Clause 5.12.1, Clause 3.4 terms).

URI: iso22989:NeuralNetworkModel

 classDiagram
    class NeuralNetworkModel
    click NeuralNetworkModel href "../NeuralNetworkModel/"
      AIModel <|-- NeuralNetworkModel
        click AIModel href "../AIModel/"

      NeuralNetworkModel : activation_function





        NeuralNetworkModel --> "0..1" ActivationFunctionType : activation_function
        click ActivationFunctionType href "../ActivationFunctionType/"



      NeuralNetworkModel : algorithm_family





        NeuralNetworkModel --> "0..1" MLAlgorithmFamily : algorithm_family
        click MLAlgorithmFamily href "../MLAlgorithmFamily/"



      NeuralNetworkModel : aliases

      NeuralNetworkModel : catastrophic_forgetting_risk

      NeuralNetworkModel : clause_reference

      NeuralNetworkModel : description

      NeuralNetworkModel : engineering_approach





        NeuralNetworkModel --> "0..1" EngineeringApproach : engineering_approach
        click EngineeringApproach href "../EngineeringApproach/"



      NeuralNetworkModel : hyperparameters

      NeuralNetworkModel : id

      NeuralNetworkModel : inference_latency_ms

      NeuralNetworkModel : model_compression_applied

      NeuralNetworkModel : model_paradigm





        NeuralNetworkModel --> "0..1" MachineLearningParadigm : model_paradigm
        click MachineLearningParadigm href "../MachineLearningParadigm/"



      NeuralNetworkModel : model_version

      NeuralNetworkModel : name

      NeuralNetworkModel : neural_network_architecture





        NeuralNetworkModel --> "0..1" NeuralNetworkArchitecture : neural_network_architecture
        click NeuralNetworkArchitecture href "../NeuralNetworkArchitecture/"



      NeuralNetworkModel : number_of_layers

      NeuralNetworkModel : number_of_parameters

      NeuralNetworkModel : parameter_count

      NeuralNetworkModel : preferred_label

      NeuralNetworkModel : see_also_uri

      NeuralNetworkModel : supports_continuous_learning

      NeuralNetworkModel : test_dataset





        NeuralNetworkModel --> "0..1" Dataset : test_dataset
        click Dataset href "../Dataset/"



      NeuralNetworkModel : trained_on

      NeuralNetworkModel : training_dataset





        NeuralNetworkModel --> "0..1" Dataset : training_dataset
        click Dataset href "../Dataset/"



      NeuralNetworkModel : training_duration

      NeuralNetworkModel : training_phenomena





        NeuralNetworkModel --> "*" NeuralNetworkPhenomenon : training_phenomena
        click NeuralNetworkPhenomenon href "../NeuralNetworkPhenomenon/"



      NeuralNetworkModel : validation_dataset





        NeuralNetworkModel --> "0..1" Dataset : validation_dataset
        click Dataset href "../Dataset/"

Inheritance

Slots

Name Cardinality and Range Description Inheritance
number_of_layers 0..1
Integer		 Number of layers in the network direct
number_of_parameters 0..1
Integer		 Approximate number of trainable parameters direct
model_paradigm 0..1
MachineLearningParadigm		 Machine-learning paradigm under which the model was trained AIModel
algorithm_family 0..1
MLAlgorithmFamily		 Algorithm family the model belongs to AIModel
engineering_approach 0..1
EngineeringApproach		 Non-learning engineering approach used (for symbolic/knowledge-based models) AIModel
training_dataset 0..1
Dataset		 Dataset used to fit the model AIModel
validation_dataset 0..1
Dataset		 Dataset used for hyperparameter tuning and model selection AIModel
test_dataset 0..1
Dataset		 Dataset used to estimate generalisation performance AIModel
hyperparameters *
String		 Free-form record of model hyperparameter settings AIModel
model_version 0..1
String		 Version identifier of the trained model artefact AIModel
trained_on 0..1
String		 Date or version reference for when the model was last trained AIModel
supports_continuous_learning 0..1
Boolean		 Whether a model supports continuous or online learning (Clause 3 AIModel
catastrophic_forgetting_risk 0..1
ConfidenceScore		 Estimated risk of catastrophic forgetting on retraining (Clause 5 AIModel
parameter_count 0..1
Integer		 Approximate count of trainable model parameters AIModel
training_duration 0..1
DurationType		 Wall-clock duration of model training, expressed as an ISO 8601 duration AIModel
inference_latency_ms 0..1
Float		 Typical end-to-end inference latency in milliseconds AIModel
model_compression_applied 0..1
Boolean		 Whether the model has had compression or distillation applied for deployment ... AIModel
neural_network_architecture 0..1
NeuralNetworkArchitecture		 Neural-network architecture, when algorithm_family is neural_network (Clauses... AIModel
activation_function 0..1
ActivationFunctionType		 Predominant activation function used in the network (Clause 3 AIModel
training_phenomena *
NeuralNetworkPhenomenon		 Training-time phenomena observed for the model (Clause 3 AIModel
id 1
Uriorcurie		 Unique CURIE or URI identifying the entity NamedEntity
name 1
String		 Human-readable label for the entity NamedEntity
description 0..1
String		 Free-text description of the entity (paraphrased; verbatim ISO text excluded) NamedEntity
clause_reference 0..1
String		 ISO/IEC 22989:2022 clause identifier (e NamedEntity
aliases *
String		 Alternative names or synonyms for the term NamedEntity
preferred_label 0..1
String		 Preferred natural-language label NamedEntity
see_also_uri *
Uriorcurie		 Pointers to related external resources or term records NamedEntity

In Subsets

Identifier and Mapping Information

Schema Source

Mappings

Mapping Type Mapped Value
self iso22989:NeuralNetworkModel
native iso22989:NeuralNetworkModel

LinkML Source

Direct

name: NeuralNetworkModel
description: AIModel realised as a neural network (Clause 5.12.1, Clause 3.4 terms).
in_subset:
- terminology
from_schema: https://w3id.org/lmodel/iso22989
is_a: AIModel
slot_usage:
  algorithm_family:
    name: algorithm_family
    ifabsent: MLAlgorithmFamily(neural_network)
attributes:
  number_of_layers:
    name: number_of_layers
    description: Number of layers in the network.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    domain_of:
    - NeuralNetworkModel
    range: integer
    minimum_value: 1
  number_of_parameters:
    name: number_of_parameters
    description: Approximate number of trainable parameters.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    domain_of:
    - NeuralNetworkModel
    range: integer
    minimum_value: 0

Induced

name: NeuralNetworkModel
description: AIModel realised as a neural network (Clause 5.12.1, Clause 3.4 terms).
in_subset:
- terminology
from_schema: https://w3id.org/lmodel/iso22989
is_a: AIModel
slot_usage:
  algorithm_family:
    name: algorithm_family
    ifabsent: MLAlgorithmFamily(neural_network)
attributes:
  number_of_layers:
    name: number_of_layers
    description: Number of layers in the network.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - NeuralNetworkModel
    range: integer
    minimum_value: 1
  number_of_parameters:
    name: number_of_parameters
    description: Approximate number of trainable parameters.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - NeuralNetworkModel
    range: integer
    minimum_value: 0
  model_paradigm:
    name: model_paradigm
    description: Machine-learning paradigm under which the model was trained.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: MachineLearningParadigm
  algorithm_family:
    name: algorithm_family
    description: Algorithm family the model belongs to.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    ifabsent: MLAlgorithmFamily(neural_network)
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: MLAlgorithmFamily
  engineering_approach:
    name: engineering_approach
    description: Non-learning engineering approach used (for symbolic/knowledge-based
      models).
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: EngineeringApproach
  training_dataset:
    name: training_dataset
    description: Dataset used to fit the model.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: Dataset
  validation_dataset:
    name: validation_dataset
    description: Dataset used for hyperparameter tuning and model selection.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: Dataset
  test_dataset:
    name: test_dataset
    description: Dataset used to estimate generalisation performance.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: Dataset
  hyperparameters:
    name: hyperparameters
    description: Free-form record of model hyperparameter settings.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: string
    multivalued: true
  model_version:
    name: model_version
    description: Version identifier of the trained model artefact.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: string
  trained_on:
    name: trained_on
    description: Date or version reference for when the model was last trained.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: string
  supports_continuous_learning:
    name: supports_continuous_learning
    description: Whether a model supports continuous or online learning (Clause 3.1.9,
      5.11.9.2).
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: boolean
  catastrophic_forgetting_risk:
    name: catastrophic_forgetting_risk
    description: Estimated risk of catastrophic forgetting on retraining (Clause 5.11.9.1).
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: ConfidenceScore
  parameter_count:
    name: parameter_count
    description: Approximate count of trainable model parameters.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: integer
    minimum_value: 0
  training_duration:
    name: training_duration
    description: Wall-clock duration of model training, expressed as an ISO 8601 duration.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: DurationType
  inference_latency_ms:
    name: inference_latency_ms
    description: Typical end-to-end inference latency in milliseconds.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: float
    minimum_value: 0.0
  model_compression_applied:
    name: model_compression_applied
    description: Whether the model has had compression or distillation applied for
      deployment (Clause 8.6.2).
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: boolean
  neural_network_architecture:
    name: neural_network_architecture
    description: Neural-network architecture, when algorithm_family is neural_network
      (Clauses 3.4, 5.12.1).
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: NeuralNetworkArchitecture
  activation_function:
    name: activation_function
    description: Predominant activation function used in the network (Clause 3.4.1).
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    - Neuron
    range: ActivationFunctionType
  training_phenomena:
    name: training_phenomena
    description: Training-time phenomena observed for the model (Clause 3.4).
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - AIModel
    range: NeuralNetworkPhenomenon
    multivalued: true
  id:
    name: id
    description: Unique CURIE or URI identifying the entity.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    slot_uri: dcterms:identifier
    identifier: true
    owner: NeuralNetworkModel
    domain_of:
    - NamedEntity
    range: uriorcurie
    required: true
  name:
    name: name
    description: Human-readable label for the entity.
    from_schema: https://w3id.org/lmodel/iso22989
    exact_mappings:
    - dcterms:title
    - schema:name
    rank: 1000
    slot_uri: schema:name
    owner: NeuralNetworkModel
    domain_of:
    - NamedEntity
    range: string
    required: true
  description:
    name: description
    description: Free-text description of the entity (paraphrased; verbatim ISO text
      excluded).
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    slot_uri: dcterms:description
    owner: NeuralNetworkModel
    domain_of:
    - NamedEntity
    range: string
  clause_reference:
    name: clause_reference
    description: ISO/IEC 22989:2022 clause identifier (e.g. "5.11.4") the element
      corresponds to.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    owner: NeuralNetworkModel
    domain_of:
    - NamedEntity
    - AutonomyAssessment
    - VerificationValidationFramework
    range: string
    pattern: ^[0-9]+(\.[0-9]+){0,3}$
  aliases:
    name: aliases
    description: Alternative names or synonyms for the term.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    slot_uri: skos:altLabel
    owner: NeuralNetworkModel
    domain_of:
    - NamedEntity
    range: string
    multivalued: true
  preferred_label:
    name: preferred_label
    description: Preferred natural-language label.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    slot_uri: skos:prefLabel
    owner: NeuralNetworkModel
    domain_of:
    - NamedEntity
    range: string
  see_also_uri:
    name: see_also_uri
    description: Pointers to related external resources or term records.
    from_schema: https://w3id.org/lmodel/iso22989
    rank: 1000
    slot_uri: rdfs:seeAlso
    owner: NeuralNetworkModel
    domain_of:
    - NamedEntity
    range: uriorcurie
    multivalued: true