Controlling non-stationarity and periodicities in time series generation using conditional invertible neural networks.
Benedikt HeidrichMarian TurowskiKaleb PhippsKai SchmiederWolfgang SüßRalf MikutVeit HagenmeyerPublished in: Appl. Intell. (2023)
Keyphrases
- neural network
- non stationary
- pattern recognition
- periodic patterns
- artificial neural networks
- random field model
- fuzzy logic
- generation process
- feed forward
- fuzzy systems
- multilayer perceptron
- mackey glass
- moving average
- symbolic representation
- fault diagnosis
- back propagation
- multi layer
- dynamic time warping
- function approximation
- radial basis function
- financial time series
- multiscale
- genetic algorithm
- chaotic time series
- data mining