Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Evolino for recurrent support vector machines  [PDF]
Juergen Schmidhuber,Matteo Gagliolo,Daan Wierstra,Faustino Gomez
Computer Science , 2005,
Abstract: Traditional Support Vector Machines (SVMs) need pre-wired finite time windows to predict and classify time series. They do not have an internal state necessary to deal with sequences involving arbitrary long-term dependencies. Here we introduce a new class of recurrent, truly sequential SVM-like devices with internal adaptive states, trained by a novel method called EVOlution of systems with KErnel-based outputs (Evoke), an instance of the recent Evolino class of methods. Evoke evolves recurrent neural networks to detect and represent temporal dependencies while using quadratic programming/support vector regression to produce precise outputs. Evoke is the first SVM-based mechanism learning to classify a context-sensitive language. It also outperforms recent state-of-the-art gradient-based recurrent neural networks (RNNs) on various time series prediction tasks.
Recurrent Support and Relevance Vector Machines Based Model with Application to Forecasting Volatility of Financial Returns  [PDF]
Altaf Hossain, Mohammed Nasser
Journal of Intelligent Learning Systems and Applications (JILSA) , 2011, DOI: 10.4236/jilsa.2011.34026
Abstract: In the recent years, the use of GARCH type (especially, ARMA-GARCH) models and computational-intelligence-based techniques—Support Vector Machine (SVM) and Relevance Vector Machine (RVM) have been successfully used for financial forecasting. This paper deals with the application of ARMA-GARCH, recurrent SVM (RSVM) and recurrent RVM (RRVM) in volatility forecasting. Based on RSVM and RRVM, two GARCH methods are used and are compared with parametric GARCHs (Pure and ARMA-GARCH) in terms of their ability to forecast multi-periodically. These models are evaluated on four performance metrics: MSE, MAE, DS, and linear regression R squared. The real data in this study uses two Asian stock market composite indices of BSE SENSEX and NIKKEI225. This paper also examines the effects of outliers on modeling and forecasting volatility. Our experiment shows that both the RSVM and RRVM perform almost equally, but better than the GARCH type models in forecasting. The ARMA-GARCH model is superior to the pure GARCH and only the RRVM with RSVM hold the robustness properties in forecasting.
Prediction of chaotic systems with multidimensional recurrent least squares support vector machines
Sun Jian-Cheng,Zhou Ya-Tong,Luo Jian-Guo,

中国物理 B , 2006,
Abstract: In this paper, we propose a multidimensional version of recurrent least squares support vector machines (MDRLS-SVM) to solve the problem about the prediction of chaotic system. To acquire better prediction performance, the high-dimensional space, which provides more information on the system than the scalar time series, is first reconstructed utilizing Takens's embedding theorem. Then the MDRLS-SVM instead of traditional RLS-SVM is used in the high-dimensional space, and the prediction performance can be improved from the point of view of reconstructed embedding phase space. In addition, the MDRLS-SVM algorithm is analysed in the context of noise, and we also find that the MDRLS-SVM has lower sensitivity to noise than the RLS-SVM.
Modelling of chaotic systems based on modified weighted recurrent least squares support vector machines
Sun Jian-Cheng,Zhang Tai-Yi,Liu Feng,

中国物理 B , 2004,
Abstract: Positive Lyapunov exponents cause the errors in modelling of the chaotic time series to grow exponentially. In this paper, we propose the modified version of the support vector machines (SVM) to deal with this problem. Based on recurrent least squares support vector machines (RLS-SVM), we introduce a weighted term to the cost function to compensate the prediction errors resulting from the positive global Lyapunov exponents. To demonstrate the effectiveness of our algorithm, we use the power spectrum and dynamic invariants involving the Lyapunov exponents and the correlation dimension as criterions, and then apply our method to the Santa Fe competition time series. The simulation results shows that the proposed method can capture the dynamics of the chaotic time series effectively.
Prediction Algorithm for Fast Fading Channels Based on Recurrent Least Squares Support Vector Machines

Xiang Zheng,Zhang Tai-yi,Sun Jian-cheng,

电子与信息学报 , 2006,
Abstract: An new method for fast fading channel prediction using Recurrent Least Squares Support Vector Machines (RLS-SVM) combined with reconstructed embedding phase space is investigated. This algorithm is based on the chaotic behavior of the mobile multipath fading channel.The phase space of these mobile multipath fading channel coefficients are reconstructed by the theory of time delays. Based on the stability and the fractal of the chaotic attractor, the fast fading channel coefficients are predicted in their phase space based on the RLS-SVM.The proposed algorithm is a better candidate for long range prediction of the fading channel in the noise context. The experiment is carried out by utilizing fading channel data which spanes 63.829 ms. The simulation results show that the better prediction performance is acquired than the AR method when the signal to noise ratio is 15dB.
Research on Spurious Co-persistence of Threshold Vector GARCH Model with Structural Change

LI Song-chen,ZHANG Shi-ying,

系统工程理论与实践 , 2007,
Abstract: Volatility persistence is an important property of finance time series.The relationship between GARCH model with structural change and IGARCH model is proved in theory,and the definition of spurious co-persistence of threshold vector GARCH model with structural change is given based on spurious persistence in volatility.Empirical results show that daily return series of Shanghai and Shenzhen have strong persistence in volatility and they are spurious co-persistent.
An Empirical Research on the Weekday Effect in the Stock Market of Shanghai by GARCH Models

TIAN Hua,LIU Qing-chun,

系统工程理论与实践 , 2003,
Abstract: This paper analyses the behaviors of the volatility in the stock Market of Shanghai using GARCH models, and find there is the weekday effect.
Comment on "Support Vector Machines with Applications"  [PDF]
Peter L. Bartlett,Michael I. Jordan,Jon D. McAuliffe
Mathematics , 2006, DOI: 10.1214/088342306000000475
Abstract: Comment on "Support Vector Machines with Applications" [math.ST/0612817]
Rejoinder to "Support Vector Machines with Applications"  [PDF]
Javier M. Moguerza,Alberto Mu?oz
Mathematics , 2006, DOI: 10.1214/088342306000000501
Abstract: Rejoinder to ``Support Vector Machines with Applications'' [math.ST/0612817]
Comment on "Support Vector Machines with Applications"  [PDF]
Grace Wahba
Mathematics , 2006, DOI: 10.1214/088342306000000457
Abstract: Comment on "Support Vector Machines with Applications" [math.ST/0612817]
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.