Disambiguation evidence for Hopfield networks via surface form

"Hopfield network"


As subject (50)

Triples where this entity appears as subject under the label "Hopfield network".

Predicate Object
belongsToField computational neuroscience
belongsToField machine learning
belongsToField neural networks
belongsToField statistical physics
convergesTo local energy minima
dynamicsMinimize energy function
hasActivationFunction sign function
hasActivationFunction threshold function
hasApproximateCapacity 0.138N for random uncorrelated patterns
hasCapacityProperty storage capacity proportional to number of neurons
hasConnectionType no self-connections
hasConnectionType symmetric weights
hasEnergyFunction Lyapunov function
hasLearningRule Hebbian learning
hasLearningRule outer-product rule
hasLimitation limited storage capacity
hasLimitation sensitivity to correlated patterns
hasLimitation spurious attractors
hasMathematicalRepresentation binary quadratic form energy
hasNodeType Ising spin
hasNodeType binary neuron
hasProperty guaranteed convergence under symmetric weights and asynchronous updates
hasStateSpace binary vectors
hasTopology fully connected network
hasUpdateDynamics deterministic dynamics
hasUpdateRule asynchronous update
hasUpdateRule synchronous update
hasVariant Hopfield networks self-linksurface differs
surface form: continuous Hopfield network
hasVariant Hopfield networks self-linksurface differs
surface form: modern Hopfield network
hasVariant stochastic Hopfield network
instanceOf associative memory model
instanceOf content-addressable memory system
instanceOf recurrent artificial neural network
introducedBy John Hopfield
introducedInYear 1982
isRelatedTo Boltzmann machines
surface form: Boltzmann machine
isRelatedTo Ising models
surface form: Ising Hopfield model
isRelatedTo Ising models
surface form: Ising model
isRelatedTo spin glass theory
isUsedFor associative memory tasks
isUsedFor combinatorial optimization
isUsedFor constraint satisfaction
isUsedFor optimization
namedAfter John Hopfield
stableStatesRepresent stored patterns
supports associative recall
supports content-addressable memory
supports error correction
supports pattern completion
supports robust retrieval from noisy inputs