Inherent Biases of Recurrent Neural Networks for Phonological Assimilation and Dissimilation.
Amanda DoucettePublished in: CMCL@EACL (2017)
Keyphrases
- recurrent neural networks
- neural network
- recurrent networks
- complex valued
- feed forward
- hidden layer
- reservoir computing
- neural model
- long short term memory
- information technology
- artificial neural networks
- nonlinear dynamic systems
- cascade correlation
- feedforward neural networks
- word recognition
- long term
- hebbian learning
- machine learning
- short term
- back propagation
- e government
- working memory
- neural models
- language learners
- text to speech synthesis