Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook

By M. Nrgaard, Ole Ravn, Niels Kjølstad Poulsen, L. K. Hansen. 2000

982 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/c94c759f760ebdc6c32df55562bafffe93231775

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Long-term time series prediction with the NARX network: An empirical evaluation (2008, background): “The Nonlinear Autoregressive model with Exogenous inputs (NARX) [26,30,33] is an important class of discrete-time nonlinear systems that can be mathematically represented as”
Virtual reference feedback tuning: a direct method for the design of feedback controllers (2002, methodology): “recalled. A similar idea, though in a special setting, has also been used in the context of control with neural networks, see [ 17 ].”
Cognitive Control (2012, positive): “In this approach, the controller itself is a neural network; alternatively, the controller may not be a neural network but uses a neural-network-based model of the system under study [7]–[10].”
Development of room temperature and relative humidity linear parametric models for an open office using BMS data (2010, methodology): “outlined in Section 5) (see [23-25]).”
Q-clouds: managing performance interference effects for QoS-aware clouds (2010, methodology): “For example, if the control being applied requires capturing system dynamics and nonlinearities, neural networks might be applicable to better estimate the relationship in Equation 1 [ 24 ].”
Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning (2005, methodology): “In each experiment of the cross-validation procedure, all the datasets are standardized, using the means and the variances of the different variables on the identification set; indeed, standardization makes the training algorithms numerically robust and leads to faster convergence Norgaard et al. (”