Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks.
Aya Abdelsalam IsmailMohamed K. GunadyLuiz PessoaHéctor Corrada BravoSoheil FeiziPublished in: NeurIPS (2019)
Keyphrases
- recurrent neural networks
- visual attention
- feed forward
- neural network
- saliency map
- recurrent networks
- reservoir computing
- visual saliency
- hidden layer
- neural model
- complex valued
- echo state networks
- feedforward neural networks
- input data
- artificial neural networks
- hebbian learning
- long short term memory
- vision system
- long term
- cascade correlation
- higher level
- real time
- neural models
- expert systems