%0 Book Section %1 citeulike:12945774 %A Lendasse, A. %A Francois, D. %A Wertz, V. %A Verleysen, M. %B Computational Science — ICCS 2003 %C Berlin %D 2003 %E Sloot, Peter M. A. %E Abramson, David %E Bogdanov, Alexander V. %E Dongarra, Jack J. %E Zomaya, Albert Y. %E Gorbachev, Yuriy E. %I Springer %K 68p30-coding-and-information-theory 62m10-time-series-auto-correlation-regression %P 417--426 %R 10.1007/3-540-44860-8\_43 %T Nonlinear Time Series Prediction by Weighted Vector Quantization %U http://dx.doi.org/10.1007/3-540-44860-8\_43 %V 2657 %X Classical nonlinear models for time series prediction exhibit improved capabilities compared to linear ones. Nonlinear regression has however drawbacks, such as overfitting and local minima problems, user-adjusted parameters, higher computation times, etc. There is thus a need for simple nonlinear models with a restricted number of learning parameters, high performances and reasonable complexity. In this paper, we present a method for nonlinear forecasting based on the quantization of vectors concatenating inputs (regressors) and outputs (predictions). Weighting techniques are applied to give more importance to inputs and outputs respectively. The method is illustrated on standard time series prediction benchmarks.

@incollection{citeulike:12945774, abstract = {{Classical nonlinear models for time series prediction exhibit improved capabilities compared to linear ones. Nonlinear regression has however drawbacks, such as overfitting and local minima problems, user-adjusted parameters, higher computation times, etc. There is thus a need for simple nonlinear models with a restricted number of learning parameters, high performances and reasonable complexity. In this paper, we present a method for nonlinear forecasting based on the quantization of vectors concatenating inputs (regressors) and outputs (predictions). Weighting techniques are applied to give more importance to inputs and outputs respectively. The method is illustrated on standard time series prediction benchmarks.}}, added-at = {2017-06-29T07:13:07.000+0200}, address = {Berlin}, author = {Lendasse, A. and Francois, D. and Wertz, V. and Verleysen, M.}, biburl = {https://www.bibsonomy.org/bibtex/2d54572c592f0cdbb4da1cb34d1eeea45/gdmcbain}, booktitle = {Computational Science — ICCS 2003}, citeulike-article-id = {12945774}, citeulike-attachment-1 = {lendasse_03_nonlinear.pdf; /pdf/user/gdmcbain/article/12945774/947250/lendasse_03_nonlinear.pdf; 6a7dd0f84db60e9e2e32659b386ed50b6e309359}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/3-540-44860-8\_43}, citeulike-linkout-1 = {http://link.springer.com/chapter/10.1007/3-540-44860-8\_43}, doi = {10.1007/3-540-44860-8\_43}, editor = {Sloot, Peter M. A. and Abramson, David and Bogdanov, Alexander V. and Dongarra, Jack J. and Zomaya, Albert Y. and Gorbachev, Yuriy E.}, file = {lendasse_03_nonlinear.pdf}, interhash = {17052901fd5b40551e0faab9c36c8649}, intrahash = {d54572c592f0cdbb4da1cb34d1eeea45}, keywords = {68p30-coding-and-information-theory 62m10-time-series-auto-correlation-regression}, pages = {417--426}, posted-at = {2014-02-03 06:15:36}, priority = {2}, publisher = {Springer}, series = {Lecture Notes in Computer Science}, timestamp = {2021-01-19T06:16:33.000+0100}, title = {{Nonlinear Time Series Prediction by Weighted Vector Quantization}}, url = {http://dx.doi.org/10.1007/3-540-44860-8\_43}, volume = 2657, year = 2003 }