Boltzmann machines

E7922

energy-based model probabilistic graphical model stochastic neural network architecture unsupervised learning model

Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (10)

Label	Occurrences
Boltzmann machine	2
Boltzmann machines canonical	2
restricted Boltzmann machines	2
Boltzmann machine learning	1
Deep Boltzmann machines	1
Learning and Relearning in Boltzmann Machines	1
Restricted Boltzmann machines	1
deep Boltzmann machines	1
deep belief networks	1
restricted Boltzmann machine	1

How this entity was disambiguated

This entity first appeared as the object of triple T93138 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Boltzmann machines
Context triple: [Geoffrey Hinton, knownFor, Boltzmann machines]

A. Deep Learning (book)
Deep Learning (book) is a foundational textbook that systematically introduces the theory and practice of modern deep neural networks, co-authored by leading researchers including Yoshua Bengio.
B. Lifelong Learning Machines program
The Lifelong Learning Machines program is a DARPA research initiative aimed at developing AI systems that can continuously learn and adapt from experience in dynamic, real-world environments.
C. SyNAPSE neuromorphic computing program
The SyNAPSE neuromorphic computing program is a DARPA initiative to develop brain-inspired electronic systems that emulate neural architectures for highly efficient, scalable cognitive computing.
D. Technical Committee on Robot Learning
The Technical Committee on Robot Learning is a specialized IEEE Robotics and Automation Society group that advances research and collaboration at the intersection of machine learning and robotics.
E. Langevin dynamics
Langevin dynamics is a stochastic approach to modeling the motion of particles in a fluid by combining deterministic forces with random thermal fluctuations, often used to simulate Brownian motion and other nonequilibrium processes.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Boltzmann machines
Target entity description: Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.

A. Deep Learning (book)
Deep Learning (book) is a foundational textbook that systematically introduces the theory and practice of modern deep neural networks, co-authored by leading researchers including Yoshua Bengio.
B. Lifelong Learning Machines program
The Lifelong Learning Machines program is a DARPA research initiative aimed at developing AI systems that can continuously learn and adapt from experience in dynamic, real-world environments.
C. SyNAPSE neuromorphic computing program
The SyNAPSE neuromorphic computing program is a DARPA initiative to develop brain-inspired electronic systems that emulate neural architectures for highly efficient, scalable cognitive computing.
D. Technical Committee on Robot Learning
The Technical Committee on Robot Learning is a specialized IEEE Robotics and Automation Society group that advances research and collaboration at the intersection of machine learning and robotics.
E. Langevin dynamics
Langevin dynamics is a stochastic approach to modeling the motion of particles in a fluid by combining deterministic forces with random thermal fluctuations, often used to simulate Brownian motion and other nonequilibrium processes.
F. None of above. chosen

Statements (48)

Predicate	Object
instanceOf	energy-based model ⓘ probabilistic graphical model ⓘ stochastic neural network architecture ⓘ unsupervised learning model ⓘ
approximationMethod	mean-field approximation ⓘ variational inference ⓘ
basedOn	Boltzmann distribution ⓘ statistical mechanics ⓘ
definesProbability	P(s) = exp(-E(s))/Z ⓘ
difficulty	partition function computation is exponential in number of units ⓘ
hasComponent	bias parameters ⓘ hidden units ⓘ visible units ⓘ
hasConnectionType	fully connected between all units in general form ⓘ
hasEnergyFunctionForm	E(v,h) = -∑_i a_i v_i -∑_j b_j h_j -∑_{i,j} v_i w_{ij} h_j -∑_{i<k} v_i u_{ik} v_k -∑_{j<l} h_j v_{jl} h_l ⓘ
hasLearningRule	contrastive divergence approximation ⓘ persistent contrastive divergence ⓘ stochastic gradient descent on log-likelihood ⓘ
hasNetworkType	recurrent neural network ⓘ
hasPartitionFunction	Z = ∑_s exp(-E(s)) ⓘ
hasProperty	Gibbs distribution over states ⓘ Markov random field structure ⓘ asynchronous stochastic updates ⓘ binary-valued units ⓘ converges to thermal equilibrium distribution ⓘ energy function ⓘ intractable exact learning for large networks ⓘ stochastic units ⓘ symmetrical weights ⓘ undirected connections ⓘ
hasSamplingMethod	Gibbs sampling ⓘ Markov chain Monte Carlo ⓘ
inspired	Boltzmann machines self-linksurface differs ⓘ surface form: Deep Boltzmann machines Deep belief networks ⓘ Boltzmann machines self-linksurface differs ⓘ surface form: Restricted Boltzmann machines
introducedBy	Geoffrey Hinton ⓘ Terrence Sejnowski ⓘ
introducedInPublication	Boltzmann machines self-linksurface differs ⓘ surface form: Learning and Relearning in Boltzmann Machines
introducedInYear	1985 ⓘ
relatedTo	Hopfield networks ⓘ Ising models ⓘ
trainingObjective	maximize data log-likelihood ⓘ
usedFor	associative memory ⓘ combinatorial optimization ⓘ density estimation ⓘ modeling complex probability distributions ⓘ representation learning ⓘ unsupervised feature learning ⓘ

How these facts were elicited

Referenced by (13)

Full triples — surface form annotated when it differs from this entity's canonical label.

Geoffrey Hinton → knownFor → Boltzmann machines ⓘ

this entity surface form: restricted Boltzmann machines

Geoffrey Hinton → knownFor → Boltzmann machines ⓘ

this entity surface form: deep belief networks

Boltzmann machines → inspired → Boltzmann machines self-linksurface differs ⓘ

this entity surface form: Restricted Boltzmann machines

Boltzmann machines → inspired → Boltzmann machines self-linksurface differs ⓘ

this entity surface form: Deep Boltzmann machines

Boltzmann machines → introducedInPublication → Boltzmann machines self-linksurface differs ⓘ

this entity surface form: Learning and Relearning in Boltzmann Machines

“A fast learning algorithm for deep belief nets” → usesModel → Boltzmann machines ⓘ

subject surface form: A fast learning algorithm for deep belief nets

this entity surface form: restricted Boltzmann machine

“A fast learning algorithm for deep belief nets” → relatedTo → Boltzmann machines ⓘ

subject surface form: A fast learning algorithm for deep belief nets

Ruslan Salakhutdinov → knownFor → Boltzmann machines ⓘ

this entity surface form: restricted Boltzmann machines

Deep belief networks → relatedTo → Boltzmann machines ⓘ

this entity surface form: deep Boltzmann machines

Terrence Sejnowski → knownFor → Boltzmann machines ⓘ

this entity surface form: Boltzmann machine learning

Hopfield networks → isRelatedTo → Boltzmann machines ⓘ

subject surface form: Hopfield network

this entity surface form: Boltzmann machine

Helmholtz machine → comparedTo → Boltzmann machines ⓘ