Recurrent Neural Networks with more flexible memory: better predictions than rough volatility.
Damien ChalletVincent RagelPublished in: CoRR (2023)
Keyphrases
- recurrent neural networks
- reservoir computing
- complex valued
- feed forward
- recurrent networks
- neural network
- rough sets
- echo state networks
- cascade correlation
- neural model
- stock market
- main memory
- memory requirements
- feedforward neural networks
- nonlinear dynamic systems
- financial time series
- memory usage
- limited memory
- long short term memory
- stock index futures
- past observations
- semi supervised