CNNs found to jump around more skillfully than RNNs: Compositional Generalization in Seq2seq Convolutional Networks.
Roberto DessìMarco BaroniPublished in: ACL (1) (2019)
Keyphrases
- echo state networks
- recurrent neural networks
- network structure
- social networks
- network analysis
- markov chain
- complex networks
- cellular neural networks
- heterogeneous networks
- network architecture
- computer networks
- database
- complex systems
- graphical models
- case study
- network model
- information systems
- machine learning
- feedforward neural networks
- neural network
- recurrent networks
- real time