Neural Networks for Lorenz Map Prediction: A Trip Through Time
arXiv:1903.07768
Abstract
In this article the Lorenz dynamical system is revived and revisited and the current state of the art results for one step ahead forecasting for the Lorenz trajectories are published. Multitask learning is shown to help learning the hard to learn z trajectory. The article is a reflection upon the evolution of neural networks with respect to the prediction performance on this canonical task.
arXiv commentTechnical Report
References in corpus (5)
- Adam: A Method for Stochastic Optimization
- On the difficulty of training Recurrent Neural Networks
- WaveNet: A Generative Model for Raw Audio
- MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
- Conditional Time Series Forecasting with Convolutional Neural Networks