Home / AIO Classes / Network / Artificial Neural Network

Artificial Neural Network

Network AIO:ArtificialNeuralNetwork NOT_REVIEWED

A network based on a collection of connected units called artificial neurons modeled after biological neurons.

Ontology IRI: https://w3id.org/aio/ArtificialNeuralNetwork

Ontology Structure & Relationships

Parent Classes

AIO:Network (Network)

Branches

Network

Annotations & Sources

Synonyms:

ANN exact
NN exact

Definition Sources:

https://en.wikipedia.org/wiki/Artificial_neural_network

Subsets:

https://w3id.org/aio/NetworkSubset

Curated AIMech Concepts Grounded to this Class

38 Concepts

Curated Concept	Kind	Mapping Relation	Rationale
Amortized Stein variational gradient descent `AIMech:AmortizedSteinVariationalGradientDescent`	Algorithms	related_match	Both primary works explicitly train stochastic neural inference networks using this sampler-fitting procedure. This relates the algorithm to a documented neural-sampler implementation class; the generic differentiable-simulator definition also permits other parameterizations. It asserts neither algorithm/model identity nor subclass or broad-match inclusion, and does not make an ANN architecture mandatory.
Attention-Based Configurable Convolutional Neural Network `AIMech:AttentionBasedConfigurableConvolutionalNeuralNetwork`	Architectures	broad_match	Learned convolutional, recurrent and classification components form a particular multimodal neural architecture; ANN is broader.
Attention-Based Convolutional Neural Network `AIMech:AttentionBasedConvolutionalNeuralNetwork`	Architectures	broad_match	Shared learned convolutional sentence encoders and attention-dependent feature computations form a specific neural architecture; the target is broader.
Attentive Pooling Network `AIMech:AttentivePoolingNetwork`	Architectures	broad_match	Learned neural encoders and a trained bilinear interaction/pooling scorer define a particular neural architecture; the target covers both convolutional and recurrent instantiations.
Autoregressive conditional restricted Boltzmann machine `AIMech:AutoregressiveConditionalRestrictedBoltzmannMachine`	Architectures	broad_match	The pinned AIO class is broader than this particular neural sequence architecture with nonlinear stochastic units and weighted connections. This mapping does not claim equivalence to a symmetric Boltzmann machine, a pure directed Bayesian network or an autoregressive language model. The latter is language-specific, while this model supports general vector sequences.
Communication Neural Network `AIMech:CommunicationNeuralNetwork`	Architectures	broad_match	Shared learned per-agent modules, continuous hidden communication and output decoders form a particular artificial neural architecture. The target is broader; the basic architecture does not require temporal recurrence, the named GCN operator, a probabilistic graphical-model task or learned attention weights.
Conditional restricted Boltzmann machine `AIMech:ConditionalRestrictedBoltzmannMachine`	Architectures	broad_match	The local family is a specific stochastic neural conditional model with weighted visible–hidden interactions and input-controlled parameters. The pinned ArtificialNeuralNetwork is broader. Classification and regression are possible uses, while their task-scoped AIO classes do not identify this architecture.
DeepLIFT `AIMech:DeepLIFT`	Algorithms	related_match	The defining method propagates contributions through an artificial neural network. The related mapping identifies that direct analysis object, not architecture identity or subclasshood.
Deep SHAP `AIMech:DeepSHAP`	Algorithms	related_match	The method directly propagates attributions through artificial neural networks. The mapping relates an analysis procedure to its analyzed system, not to an equivalent architecture.
Deep Sets `AIMech:DeepSets`	Architectures	broad_match	The source constructs trainable neural transformations and shared neural layers for set-valued inputs; the artificial-neural-network target has broader scope.
Deep Sets++ `AIMech:DeepSetsPlusPlus`	Architectures	broad_match	The source modifies learned neural encoder blocks with residual paths and normalization; ArtificialNeuralNetwork is the broader architecture class.
End-to-End Memory Network `AIMech:EndToEndMemoryNetwork`	Architectures	broad_match	Learned memory and query embeddings, differentiable attention and a neural prediction head form a particular artificial neural architecture; the target is broader.
Graph attention network v2 `AIMech:GATv2`	Architectures	broad_match	The specified graph attentional layers form an artificial neural architecture, so the artificial-neural-network target is broader.
GENET `AIMech:GENET`	Architectures	broad_match	The pinned target is a network of connected artificial-neuron units. GENET is a specific connectionist network of label/constraint nodes with activation and inhibitory weight-update rules, so the AIO target is broader than this local architecture. No content-addressable Hopfield identity is asserted, and general constraint connections are asymmetric; the broader ANN mapping does not imply universal symmetric connectivity.
Gated Graph Neural Network `AIMech:GatedGraphNeuralNetwork`	Architectures	broad_match	Learned graph message transformations, gated hidden updates and neural readouts form a particular artificial neural architecture; this target is broader.
Gated Graph Sequence Neural Network `AIMech:GatedGraphSequenceNeuralNetwork`	Architectures	broad_match	Gated graph propagation, learned output heads and annotation-update networks make this a particular artificial neural architecture; the target is broader.
Gradient-weighted class activation mapping `AIMech:GradCAM`	Algorithms	related_match	The method analyzes convolutional artificial-neural-network activations and target gradients. This is a direct analysis relation, not architecture identity.
Graph attention network `AIMech:GraphAttentionNetwork`	Architectures	broad_match	Graph attentional layers are learned neural computations, so the general artificial-neural-network target is broader.
Graph isomorphism network `AIMech:GraphIsomorphismNetwork`	Architectures	broad_match	The architecture uses learned multilayer perceptrons to transform graph-node states; the AIO neural-network category is broader.
GraphSAGE `AIMech:GraphSAGE`	Architectures	broad_match	Learned aggregation and transformation layers form an artificial neural network; this target is broader than the specific graph architecture.
Grid Long Short-Term Memory `AIMech:GridLongShortTermMemory`	Architectures	broad_match	The grid of learned gated transforms is a specific neural architecture family; the target is broader across its feed-forward, sequential and spatial instantiations.
Guarded discrete stochastic network `AIMech:GuardedDiscreteStochasticNetwork`	Architectures	broad_match	The inspected AIO target is a broader class of connected artificial-neuron units. This specific main-plus-guard architecture uses weighted inputs, binary threshold outputs and coupled neural units to encode a finite CSP. The target does not specify the guard asymmetry or row update. The mapping is not exact identity with HopfieldNetwork, whose pinned definition requires symmetric connectivity and content-addressable memory.
Guided Grad-CAM `AIMech:GuidedGradCAM`	Algorithms	related_match	The fused visualization analyzes artificial-neural-network behavior through convolutional activations and backward input-space signals; it is an analysis method, not a network architecture.
Integrated gradients `AIMech:IntegratedGradients`	Mathematical Methods	related_match	The method attributes outputs of artificial neural networks to their inputs in the defining paper. This direct analysis relationship does not make the method a neural-network architecture.
Interaction Network `AIMech:InteractionNetwork`	Architectures	broad_match	Shared learned multilayer relation and object functions make this a particular artificial neural architecture. The target is broader. The graph-convolutional target references a distinct named GCN construction; graph use alone does not establish equivalence. Temporal recurrence and probabilistic graphical-model tasks are not required identities.
Jumping Knowledge network `AIMech:JumpingKnowledgeNetwork`	Architectures	broad_match	The source builds a neural architecture from neighborhood-aggregation layers and a final learned or pooling combination; the artificial-neural-network target is broader.
Key-Value Memory Network `AIMech:KeyValueMemoryNetwork`	Architectures	broad_match	Learned embeddings, soft attention, query transforms and answer scoring define a particular artificial neural architecture; the AIO target is broader.
Layer-wise relevance propagation `AIMech:LayerWiseRelevancePropagation`	Mathematical Methods	related_match	The paper explicitly constructs LRP for artificial neural networks. This related mapping records that supported analysis relationship while retaining LRP's additional kernel-classifier scope; it asserts neither equivalence nor exclusive applicability.
Mixture density network `AIMech:MixtureDensityNetwork`	Architectures	broad_match	The local identity is a neural architecture with a conditional-mixture output parameterization, so the inspected AIO artificial-neural-network class is broader. DeepFeedForwardNetwork requires multiple hidden layers through its parent and is not a necessary superclass of the original one-hidden-layer construction. Perceptron is defined as a binary linear classifier, and MixtureofExpertsLLM has a distinct language-model and sparse-routing scope.
PointNet `AIMech:PointNet`	Architectures	broad_match	Shared neural feature extractors, learned transforms and neural prediction paths make this a specific artificial neural architecture.
PointNet++ `AIMech:PointNetPlusPlus`	Architectures	broad_match	Hierarchical learned PointNet modules and prediction layers form a specific artificial neural architecture.
Retentive network `AIMech:RetNet`	Architectures	broad_match	Learned retention projections, gates and feedforward transformations compose a neural architecture. ArtificialNeuralNetwork is broader and does not incorrectly identify retention as Transformer attention.
Set Transformer `AIMech:SetTransformer`	Architectures	broad_match	The source specifies a learned neural encoder, attention pooling and output network. ArtificialNeuralNetwork is broader without adding a language-model restriction.
Set Transformer++ `AIMech:SetTransformerPlusPlus`	Architectures	broad_match	The revised attention encoder is a learned neural architecture; the broader artificial-neural-network class does not equate it with a language model or its component attention operation.
SimNet `AIMech:SimNet`	Architectures	broad_match	SimNet is a specific learned neural architecture family; the pinned generic artificial-neural-network target is broader.
SmoothGrad `AIMech:SmoothGrad`	Algorithms	related_match	The defining method smooths sensitivity maps of artificial-neural-network outputs. This direct analysis relationship is not an assertion that SmoothGrad is itself a network.
Temporal restricted Boltzmann machine `AIMech:TemporalRestrictedBoltzmannMachine`	Architectures	broad_match	The pinned AIO class is broader than this particular neural sequence architecture with nonlinear stochastic units and weighted connections. This mapping does not claim equivalence to a symmetric Boltzmann machine, a pure directed Bayesian network or an autoregressive language model. The latter is language-specific, while this model supports general vector sequences.
Vertex Attention Interaction Network `AIMech:VertexAttentionInteractionNetwork`	Architectures	broad_match	Shared learned encoders, attention-weighted communication and a learned decoder make VAIN a particular artificial neural architecture; the generic AIO target is broader. No equivalence to a named GCN, Transformer or individual attention layer is asserted.

Import Provenance & Upstream Synchronization

Source Repo: AIO GitHub

Release Version: aio.json

Commit: 397851c547…

License: CC-BY-4.0

Imported At: 2026-10-10T07:34:10Z

SHA256: 8f741d71408c…

Source File: data/aio/ArtificialNeuralNetwork.yaml