Emergence of grid-like representations by training recurrent neural networks to perform spatial localization.
Christopher J. CuevaXue-Xin WeiPublished in: CoRR (2018)
Keyphrases
- recurrent neural networks
- echo state networks
- recurrent networks
- feedforward neural networks
- neural network
- feed forward
- reservoir computing
- hidden layer
- spatio temporal
- complex valued
- neural model
- feed forward neural networks
- training algorithm
- long short term memory
- nonlinear dynamic systems
- spatial information
- grid computing
- grid cells
- artificial neural networks
- multi layer perceptron
- training process
- supervised learning
- training set
- spatial relationships
- grid environment
- spatial and temporal
- long term
- control system
- cascade correlation