AIMech AI
Home / AIO Classes / Network / Boltzmann Machine Network

Boltzmann Machine Network

Network AIO:BoltzmannMachineNetwork NOT_REVIEWED
A symmetrically connected network that is a type of stochastic recurrent neural network and Markov random field.
Ontology IRI: https://w3id.org/aio/BoltzmannMachineNetwork

Ontology Structure & Relationships

Parent Classes
Branches
Network
Axiomatic Relationships

Annotations & Sources

Synonyms:
  • BM exact
  • Sherrington–Kirkpatrick model with external field exact
  • stochastic Hopfield network with hidden units exact
  • stochastic Ising-Lenz-Little model exact
Definition Sources:
Subsets:
  • https://w3id.org/aio/NetworkSubset

Curated AIMech Concepts Grounded to this Class

4 Concepts
Curated Concept Kind Mapping Relation Rationale
Boltzmann chain
AIMech:BoltzmannChain
 Model Families broad_match The source explicitly defines the temporal model as a tied-weight Boltzmann machine with categorical units and undirected pair interactions. The AIO target describes the broader symmetrically connected stochastic network/Markov-random-field family; the selected temporal graphs are a narrower construction.
Fully factorized mean-field inference
AIMech:FullyFactorizedMeanFieldInference
 Mathematical Methods related_match The primary derivation approximates the binary pairwise Boltzmann distribution and its hidden-variable statistics. The AIO target is the probabilistic network family, not the approximation procedure. This direct method-to-model relation does not restrict the method to one trained network.
Mean-field Boltzmann learning
AIMech:MeanFieldBoltzmannLearning
 Algorithms related_match The algorithm estimates parameter updates for the symmetrically connected stochastic network named by the AIO target. A learning algorithm is distinct from the network family it trains.
Structured mean-field inference
AIMech:StructuredMeanFieldInference
 Mathematical Methods related_match The primary derivation approximates the binary pairwise Boltzmann distribution and its hidden-variable statistics. The AIO target is the probabilistic network family, not the approximation procedure. This direct method-to-model relation does not restrict the method to one trained network.

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/BoltzmannMachineNetwork.yaml