Hebbian learning
E260043
Hebbian learning is a neurobiological and computational learning principle often summarized as "cells that fire together wire together," where the connection between neurons is strengthened when they are activated simultaneously.
All labels observed (2)
| Label | Occurrences |
|---|---|
| Hebbian learning canonical | 3 |
| Hebbian theory | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T2373577 — 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: Hebbian learning Context triple: [Hopfield network, hasLearningRule, Hebbian learning]
-
A.
Perceptrons
Perceptrons is a seminal 1969 book by Marvin Minsky and Seymour Papert that critically analyzes the capabilities and limitations of early neural network models, profoundly influencing the development of artificial intelligence and machine learning.
-
B.
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.
-
C.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
D.
RBM
RBM is a global partnership initiative dedicated to coordinating and scaling up efforts to prevent, control, and ultimately eliminate malaria worldwide.
-
E.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
- 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: Hebbian learning Target entity description: Hebbian learning is a neurobiological and computational learning principle often summarized as "cells that fire together wire together," where the connection between neurons is strengthened when they are activated simultaneously.
-
A.
Perceptrons
Perceptrons is a seminal 1969 book by Marvin Minsky and Seymour Papert that critically analyzes the capabilities and limitations of early neural network models, profoundly influencing the development of artificial intelligence and machine learning.
-
B.
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.
-
C.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
D.
RBM
RBM is a global partnership initiative dedicated to coordinating and scaling up efforts to prevent, control, and ultimately eliminate malaria worldwide.
-
E.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
- F. None of above. chosen
Statements (47)
| Predicate | Object |
|---|---|
| instanceOf |
learning rule
ⓘ
synaptic plasticity mechanism ⓘ unsupervised learning principle ⓘ |
| appliesTo |
excitatory synapses
ⓘ
synaptic weight changes ⓘ |
| basedOn | correlation of pre- and postsynaptic activity ⓘ |
| biologicalBasis | activity-dependent synaptic modification ⓘ |
| category |
Neural network learning rules
ⓘ
Neuroplasticity ⓘ Unsupervised learning algorithms ⓘ |
| contrastedWith |
backpropagation
ⓘ
error-driven learning ⓘ |
| coreIdea | neurons that fire together wire together ⓘ |
| describes | activity-dependent synaptic strengthening ⓘ |
| field |
artificial neural networks
ⓘ
computational neuroscience ⓘ machine learning ⓘ neuroscience ⓘ |
| formalizedAs | weight change proportional to product of pre- and postsynaptic activities ⓘ |
| hasLimitation | unbounded growth of synaptic weights ⓘ |
| hasVariant |
Oja rule
ⓘ
covariance rule ⓘ spike-timing-dependent plasticity ⓘ |
| influenced |
associative memory models
ⓘ
competitive learning algorithms ⓘ development of artificial neural networks ⓘ self-organizing maps ⓘ |
| involves |
co-activation of neurons
ⓘ
long-term potentiation ⓘ |
| mathematicalForm | Δw ∝ x·y ⓘ |
| namedAfter |
Donald Hebb
ⓘ
surface form:
Donald Olding Hebb
|
| proposedBy |
Donald Hebb
ⓘ
surface form:
Donald O. Hebb
|
| publication | The Organization of Behavior ⓘ |
| publicationYear | 1949 ⓘ |
| relatedTo |
Hebbian plasticity
ⓘ
correlation-based learning ⓘ unsupervised feature learning ⓘ |
| requires |
normalization of synaptic strengths
ⓘ
stabilizing mechanisms ⓘ |
| supports |
associative learning
ⓘ
cell assembly formation ⓘ memory storage ⓘ pattern completion ⓘ |
| usedIn |
Hopfield networks
ⓘ
associative memory networks ⓘ models of cortical development ⓘ models of sensory map formation ⓘ |
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: Hebbian learning Description of subject: Hebbian learning is a neurobiological and computational learning principle often summarized as "cells that fire together wire together," where the connection between neurons is strengthened when they are activated simultaneously.
Referenced by (4)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
Hopfield network
subject surface form:
Hebb Award
subject surface form:
Hebb Award
this entity surface form:
Hebbian theory