Helmholtz machine
E260031
generative neural network model
latent variable model
probabilistic generative model
unsupervised learning model
The Helmholtz machine is a pioneering generative neural network model that learns internal representations by using separate recognition and generative pathways to perform unsupervised learning.
All labels observed (2)
| Label | Occurrences |
|---|---|
| Helmholtz machine canonical | 1 |
| wake-sleep algorithm | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T2373510 — 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: Helmholtz machine Context triple: [Terrence Sejnowski, knownFor, Helmholtz machine]
-
A.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
B.
“A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
-
C.
Deep belief networks
Deep belief networks are a class of deep generative neural network models composed of stacked layers of latent variables, typically built from restricted Boltzmann machines, used for unsupervised feature learning and representation.
-
D.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
-
E.
Auto-Encoding Variational Bayes
Auto-Encoding Variational Bayes is the foundational 2013 paper by Kingma and Welling that introduced variational autoencoders, a generative model framework combining deep learning with variational Bayesian inference.
- 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: Helmholtz machine Target entity description: The Helmholtz machine is a pioneering generative neural network model that learns internal representations by using separate recognition and generative pathways to perform unsupervised learning.
-
A.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
B.
“A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
-
C.
Deep belief networks
Deep belief networks are a class of deep generative neural network models composed of stacked layers of latent variables, typically built from restricted Boltzmann machines, used for unsupervised feature learning and representation.
-
D.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
-
E.
Auto-Encoding Variational Bayes
Auto-Encoding Variational Bayes is the foundational 2013 paper by Kingma and Welling that introduced variational autoencoders, a generative model framework combining deep learning with variational Bayesian inference.
- F. None of above. chosen
Statements (44)
| Predicate | Object |
|---|---|
| instanceOf |
generative neural network model
ⓘ
latent variable model ⓘ probabilistic generative model ⓘ unsupervised learning model ⓘ |
| comparedTo |
Boltzmann machines
ⓘ
surface form:
Boltzmann machine
autoencoder ⓘ |
| field |
artificial neural networks
ⓘ
computational neuroscience ⓘ machine learning ⓘ |
| goal |
learn generative model of data
ⓘ
model sensory data distribution ⓘ perform approximate Bayesian inference ⓘ |
| hasAdvantage |
biologically plausible learning scheme
ⓘ
separate pathways for inference and generation ⓘ |
| hasArchitecture |
layered stochastic neural network
ⓘ
top-down generative model with bottom-up recognition model ⓘ |
| hasComponent |
generative network
ⓘ
recognition network ⓘ |
| hasConcept |
sleep phase updates recognition weights
ⓘ
wake phase updates generative weights ⓘ |
| hasLearningType | unsupervised learning ⓘ |
| hasLimitation |
approximate inference quality depends on recognition network
ⓘ
training can be difficult ⓘ |
| hasProperty |
approximate inference
ⓘ
bottom-up recognition connections ⓘ energy-based interpretation ⓘ hierarchical structure ⓘ learns internal representations ⓘ separate recognition and generative pathways ⓘ stochastic latent variables ⓘ top-down generative connections ⓘ |
| hasTrainingObjective |
maximize data likelihood approximately
ⓘ
minimize divergence between recognition and generative distributions ⓘ |
| inspired |
modern deep generative models
ⓘ
variational autoencoders ⓘ
surface form:
variational autoencoder
|
| namedAfter | Hermann von Helmholtz ⓘ |
| trainedBy |
sleep phase
ⓘ
wake phase ⓘ |
| usedFor |
density estimation
ⓘ
representation learning ⓘ unsupervised feature extraction ⓘ |
| uses |
local learning rules
ⓘ
stochastic units ⓘ |
| usesLearningRule |
Helmholtz machine
self-linksurface differs
ⓘ
surface form:
wake-sleep algorithm
|
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Helmholtz machine Description of subject: The Helmholtz machine is a pioneering generative neural network model that learns internal representations by using separate recognition and generative pathways to perform unsupervised learning.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
wake-sleep algorithm