Statements (33)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:convolutional_neural_network
|
| gptkbp:abbreviation |
gptkb:MLP
|
| gptkbp:application |
gptkb:dictionary
function approximation pattern recognition regression |
| gptkbp:developedBy |
1980s
|
| gptkbp:field |
gptkb:artificial_intelligence
gptkb:machine_learning |
| gptkbp:hasComponent |
hidden layer
input layer output layer |
| gptkbp:hasProperty |
supervised learning
multiple layers fully connected layers nonlinear mapping universal approximator |
| https://www.w3.org/2000/01/rdf-schema#label |
Multilayer Perceptron
|
| gptkbp:inventedBy |
gptkb:Frank_Rosenblatt
|
| gptkbp:limitation |
cannot model temporal sequences
vanishing gradient problem prone to overfitting |
| gptkbp:relatedTo |
gptkb:convolutional_neural_network
deep learning recurrent neural network |
| gptkbp:type |
gptkb:feedforward_neural_network
|
| gptkbp:uses |
gptkb:ReLU_function
backpropagation sigmoid function activation function tanh function |
| gptkbp:bfsParent |
gptkb:convolutional_neural_network
|
| gptkbp:bfsLayer |
5
|