DISCRETE- vs. CONTINUOUS-TIME NONLINEAR SIGNAL PROCESSING OF Cu ELECTRODISSOLUTION DATA

By R. Rico-Martínez, Katharina Krischer, Ioannis G. Kevrekidis, M. Kube, J. L. Hudson. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Steven L. Brunton
2. Bernd R. Noack
3. Pantelis R. Vlachas
4. J. Nathan Kutz
5. Petros Koumoutsakos
6. Themistoklis P. Sapsis
7. Wonmin Byeon
8. Zhong Y. Wan

Citations in the corpus

• Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks (2018, background): “Similarly, other machine learning techniques based on multi-layer perceptrons (MLP) [39], echo state networks (ESNs) [40,41] or radial basis functions [42,43] have been successful, albeit only for low-order dynamical systems.”
• Machine Learning for Fluid Mechanics (2019, background): “…into account the inherent order of the data, thus augmenting some of the pioneering applications of classical neural networks on signal processing (Rico-Martinez et al. 1992) However, the effectiveness of RNNs has been hindered by diminishing or exploding gradients that emerge during their…”