multilayer perceptron (MLP)

GPTKB entity

Statements (41)
Predicate Object
gptkbp:instanceOf gptkb:model
gptkb:convolutional_neural_network
gptkbp:canBe gptkb:dictionary
regression
gptkbp:canBeTrainedWith gradient descent
stochastic gradient descent
gptkbp:canUseActivationFunction gptkb:ReLU
sigmoid
tanh
gptkbp:distinctFrom gptkb:convolutional_neural_network
recurrent neural network
gptkbp:hasApplication speech recognition
diagnosis
financial forecasting
image recognition
gptkbp:hasComponent hidden layer
input layer
output layer
https://www.w3.org/2000/01/rdf-schema#label multilayer perceptron (MLP)
gptkbp:isUniversalApproximator true
gptkbp:limitation vanishing gradient problem
cannot model sequential data
prone to overfitting
gptkbp:parameter weights
biases
gptkbp:popularizedBy gptkb:Geoffrey_Hinton
gptkbp:requires labeled data
gptkbp:startYear 1958
gptkbp:type gptkb:feedforward_neural_network
gptkbp:usedIn data compression
deep learning
function approximation
pattern recognition
supervised learning
time series prediction
feature extraction
gptkbp:uses backpropagation
activation function
gptkbp:wasFirstDescribedBy gptkb:Frank_Rosenblatt
gptkbp:bfsParent gptkb:feedforward_neural_network
gptkbp:bfsLayer 6