Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network.
Chengyi WangShuangzhi WuShujie LiuPublished in: CoRR (2019)
Keyphrases
- recurrent neural networks
- neural network
- complex valued
- feed forward
- reservoir computing
- recurrent networks
- feedforward neural networks
- echo state networks
- nonlinear dynamic systems
- hidden layer
- viterbi algorithm
- long short term memory
- neural model
- artificial neural networks
- hidden markov models
- distribution network
- neuro fuzzy
- adaptive neural
- fuzzy sets
- fuzzy logic