Improved PAC-Bayesian Bounds for Linear Regression

Autor: Mihaly Petreczky, Alireza Fakhrizadeh Esfahani, Vera Shalaeva, Pascal Germain

Publikováno v: AAAI
AAAI 2020-Thirty-Fourth AAAI Conference on Artificial Intelligence
AAAI 2020-Thirty-Fourth AAAI Conference on Artificial Intelligence, Feb 2020, New York, United States

International audience; In this paper, we improve the PAC-Bayesian error bound for linear regression derived in Germain et al. [10]. The improvements are twofold. First, the proposed error bound is tighter, and converges to the generalization loss wi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::082c6f9fa33c87055b2bb94522de4854

Challenges in the Identification of Discrete Time Block Oriented Models for Continuous Time Nonlinear Systems**This work was supported in part by the Fund for Scientific Research (FWO-Vlaanderen), by the Flemish Government (Methusalem), the Belgian Government through the Inter university Poles of Attraction (IAP VII) Program, and by the ERC advanced grant SNLSID, under contract 320378

Autor: Rishi Relan, M. Vaes, Joannes Schoukens, Alireza Fakhrizadeh Esfahani

Publikováno v: IFAC-PapersOnLine. 48:596-601

Block oriented nonlinear models capture the dynamics of a nonlinear system with linear dynamic sub-systems (L), the nonlinear behavior is modeled using static nonlinear subblocks (N). In this paper we focus on three important theoretical and practica

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e30422fb5a41d856f7c1d32046f967a5
https://doi.org/10.1016/j.ifacol.2015.12.194

A nonlinear state-space approach to hysteresis identification

Autor: Gaëtan Kerschen, Joannes Schoukens, Jean-Philippe Noël, Alireza Fakhrizadeh Esfahani

Most studies tackling hysteresis identification in the technical literature follow white-box approaches, i.e. they rely on the assumption that measured data obey a specific hysteretic model. Such an assumption may be a hard requirement to handle in r

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f697af00c74b24931210f64702ef1ed9
http://arxiv.org/abs/1610.09138

Hysteresis Identification Using Nonlinear State-Space Models

Autor: Joannes Schoukens, Jean-Philippe Noël, Alireza Fakhrizadeh Esfahani, Gaëtan Kerschen

Publikováno v: Nonlinear Dynamics, Volume 1 ISBN: 9783319297385

Most studies tackling hysteresis identification in the technical literature follow white-box approaches, i.e. they rely on the assumption that measured data obey a specific hysteretic model. Such an assumption may be a hard requirement to handle in r

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9e40d8eb55de871b4e8ff5a8d9e6bbb8
https://doi.org/10.1007/978-3-319-29739-2_30

Using a polynomial decoupling algorithm for state-space identification of a Bouc-Wen system

Autor: Alireza Fakhrizadeh Esfahani, Philippe Dreesen, Koen Tiels, Jean-Philippe Noel, Johan Schoukens

Publikováno v: Vrije Universiteit Brussel

The polynomial nonlinear state space (PNLSS) approach 1] is a powerful tool for modeling nonlinear systems. A PNLSS model consists of a discrete-time linear state space model, extended with polynomials in the state and the output equation.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c21b424aa2c3ae8728c226b88a013279
https://researchportal.vub.be/en/publications/a3ebbbd2-b450-41f2-8376-0d666ac7a490