Dynamic systems identification with Gaussian processes

By Jus Kocijan, Agathe Girard, B. Banko, Roderick Murray-Smith. 2005

245 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Statistical and Nonlinear Physics

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

1. Sergey Levine
2. Marc Peter Deisenroth
3. Carl E. Rasmussen
4. Jan Peters
5. Pieter Abbeel
6. Eric P. Xing
7. Zhiting Hu
8. Dieter Fox

In Control and Systems Engineering

1. Jan Peters
2. Sergey Levine
3. Marc Peter Deisenroth
4. Pieter Abbeel
5. Carl E. Rasmussen
6. Duy Nguyen-Tuong
7. Dieter Fox
8. Gerhard Neumann

In Statistical and Nonlinear Physics

1. Carl E. Rasmussen
2. Eric P. Xing
3. Zhiting Hu
4. Andrew Gordon Wilson
5. Roger Frigola
6. Dieter Fox
7. Jonathan Ko
8. Yew-Soon Ong

Citations in the corpus

• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems (2018, neutral): “Specifically, in the context of identifying nonlinear dynamics, there exist several deterministic and probabilistic tools including radial basis functions [6], neural networks [7], Gaussian processes [8, 9, 10, 11, 12], and nonlinear auto-regressive models such as NARMAX [13] and recurrent neural ne”
• Probabilistic Recurrent State-Space Models (2018, methodology): “The benchmarks datasets are composed of popular sys-tem identification datasets from related work (Narendra & Parthasarathy, 1990; Kocijan et al., 2005; Mattos et al., 2016).”
• Gaussian process model based predictive control (2004, methodology): “[14], [13], [3], [20], [9], [10] and some control algorithms based on such are described in [15], [4].”
• Explicit stochastic predictive control of combustion plants based on Gaussian process models (2008, unknown): “and by the log predictive density error (LD) ( Kocijan, Girard, Banko & Murray-Smith, 2005 ):”
• Financial modeling using Gaussian process models (2011, unknown): “978-1-4577-1425-2/11/$26.00 ©2011 IEEE”
• When Gaussian Process Meets Big Data: A Review of Scalable GPs (2018, background): “Due to the simplicity and applicability, GP-NARX has been well studied and extended to achieve robust predictions against outliers [218], local modeling by incorporating prior information [219], and higher-order frequency response functions [220].”
• GP-BayesFilters: Bayesian filtering using Gaussian process prediction and observation models (2008, background): “The application of GPs to prediction modeling or dynamical system identification has been done by several researchers (Girard et al. 2005; Kocijan et al. 2003).”
• Learning Scalable Deep Kernels with Recurrent Structure (2016, methodology): “We used a number of classical baselines: NARX (Lin et al., 1996), GP-NARX models (Kocijan et al., 2005), and classical RNN and LSTM architectures.”
• Integrated pre-processing for Bayesian nonlinear system identification with Gaussian processes (2013, methodology): “Kocijan et al. [5] presented a NARX model where the nonlinearity is captured using Gaussian process regression.”