Delta Rule

GPTKB entity

Statements (23)
Predicate Object
gptkbp:instanceOf Learning Algorithm
gptkbp:alsoKnownAs Widrow-Hoff rule
gptkbp:appliesTo Single-layer Networks
gptkbp:basisFor Backpropagation Algorithm
gptkbp:category Gradient Descent Method
gptkbp:field gptkb:Machine_Learning
gptkb:artificial_intelligence
https://www.w3.org/2000/01/rdf-schema#label Delta Rule
gptkbp:introduced gptkb:Marcian_Hoff
gptkb:Bernard_Widrow
gptkbp:introducedIn 1960
gptkbp:notRecommendedFor Non-differentiable Activation Functions
gptkbp:reduces gptkb:Mean_Squared_Error
gptkbp:relatedTo Backpropagation
Perceptron Learning Rule
gptkbp:requires Differentiable Activation Function
gptkbp:updated Weights
gptkbp:updateFormula w_new = w_old + η (target - output) x
gptkbp:usedFor Supervised Learning
gptkbp:usedIn gptkb:Perceptron
gptkb:Artificial_Neural_Networks
gptkbp:bfsParent gptkb:Adaptive_Linear_Neuron
gptkbp:bfsLayer 8