Statements (68)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:model
gptkb:convolutional_neural_network |
| gptkbp:abbreviation |
gptkb:RNN
|
| gptkbp:alternativeName |
stochastic_recurrent_neural_network
|
| gptkbp:canBeTrainedBy |
gptkb:backpropagation_through_time
variational inference |
| gptkbp:firstDescribed |
1980s
|
| gptkbp:hasApplication |
machine translation
speech recognition speech synthesis text generation sentiment analysis chatbots language modeling music generation video prediction |
| gptkbp:hasComponent |
recurrent neural network
hidden state input layer output layer recurrent connection |
| gptkbp:hasProperty |
memory of previous inputs
nonlinear activation functions parameter sharing across time steps stochasticity randomness in hidden states |
| gptkbp:hasVariant |
gptkb:bidirectional_RNN
gptkb:echo_state_network gptkb:long_short-term_memory gated recurrent unit |
| gptkbp:implementedIn |
gptkb:TensorFlow
gptkb:Keras gptkb:Theano gptkb:PyTorch |
| gptkbp:input |
sequential data
|
| gptkbp:inventedBy |
gptkb:Geoffrey_Hinton
gptkb:John_Hopfield gptkb:David_Rumelhart gptkb:Ronald_J._Williams |
| gptkbp:limitation |
exploding gradient problem
vanishing gradient problem |
| gptkbp:output |
sequential data
single value |
| gptkbp:relatedTo |
gptkb:convolutional_neural_network
gptkb:feedforward_neural_network probabilistic graphical model Bayesian neural network variational recurrent neural network |
| gptkbp:subclassOf |
gptkb:model
connectionist model |
| gptkbp:trainer |
gptkb:backpropagation_through_time
|
| gptkbp:usedFor |
machine translation
natural language processing speech recognition time series prediction sequence modeling |
| gptkbp:usedIn |
time series prediction
handwriting recognition generative modeling anomaly detection sequence modeling language modeling music generation video analysis |
| gptkbp:bfsParent |
gptkb:artificial_neural_networks
gptkb:model gptkb:convolutional_neural_network |
| gptkbp:bfsLayer |
5
|