Standard
Regularized sparse kernel slow feature analysis. / Böhmer, W.
; Grunewalder, S.; Nickisch, H. et al.
Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011. ed. / D. Gunopulos; T. Hoffmann; D. Malerba; M. Vazirgiannis. Berlin: Springer, 2011. p. 235-248 (Lecture Notes in Computer Science; Vol. 6911).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Böhmer, W
, Grunewalder, S, Nickisch, H & Obermayer, K 2011,
Regularized sparse kernel slow feature analysis. in D Gunopulos, T Hoffmann, D Malerba & M Vazirgiannis (eds),
Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011. Lecture Notes in Computer Science, vol. 6911, Springer, Berlin, pp. 235-248.
https://doi.org/10.1007/978-3-642-23780-5_25APA
Böhmer, W.
, Grunewalder, S., Nickisch, H., & Obermayer, K. (2011).
Regularized sparse kernel slow feature analysis. In D. Gunopulos, T. Hoffmann, D. Malerba, & M. Vazirgiannis (Eds.),
Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011 (pp. 235-248). (Lecture Notes in Computer Science; Vol. 6911). Springer.
https://doi.org/10.1007/978-3-642-23780-5_25Vancouver
Böhmer W
, Grunewalder S, Nickisch H, Obermayer K.
Regularized sparse kernel slow feature analysis. In Gunopulos D, Hoffmann T, Malerba D, Vazirgiannis M, editors, Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011. Berlin: Springer. 2011. p. 235-248. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-23780-5_25
Author
Bibtex
@inproceedings{e277019582314bddb6933316ceb2730d,
title = "Regularized sparse kernel slow feature analysis",
abstract = "This paper develops a kernelized slow feature analysis (SFA) algorithm. SFA is an unsupervised learning method to extract features which encode latent variables from time series. Generative relationships are usually complex, and current algorithms are either not powerful enough or tend to over-fit. We make use of the kernel trick in combination with sparsification to provide a powerful function class for large data sets. Sparsity is achieved by a novel matching pursuit approach that can be applied to other tasks as well. For small but complex data sets, however, the kernel SFA approach leads to over-fitting and numerical instabilities. To enforce a stable solution, we introduce regularization to the SFA objective. Versatility and performance of our method are demonstrated on audio and video data sets.",
author = "W. B{\"o}hmer and S. Grunewalder and H. Nickisch and K. Obermayer",
year = "2011",
doi = "10.1007/978-3-642-23780-5_25",
language = "English",
isbn = "9783642237799",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "235--248",
editor = "D. Gunopulos and Hoffmann, {T. } and D. Malerba and M. Vazirgiannis",
booktitle = "Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011",
}
RIS
TY - GEN
T1 - Regularized sparse kernel slow feature analysis
AU - Böhmer, W.
AU - Grunewalder, S.
AU - Nickisch, H.
AU - Obermayer, K.
PY - 2011
Y1 - 2011
N2 - This paper develops a kernelized slow feature analysis (SFA) algorithm. SFA is an unsupervised learning method to extract features which encode latent variables from time series. Generative relationships are usually complex, and current algorithms are either not powerful enough or tend to over-fit. We make use of the kernel trick in combination with sparsification to provide a powerful function class for large data sets. Sparsity is achieved by a novel matching pursuit approach that can be applied to other tasks as well. For small but complex data sets, however, the kernel SFA approach leads to over-fitting and numerical instabilities. To enforce a stable solution, we introduce regularization to the SFA objective. Versatility and performance of our method are demonstrated on audio and video data sets.
AB - This paper develops a kernelized slow feature analysis (SFA) algorithm. SFA is an unsupervised learning method to extract features which encode latent variables from time series. Generative relationships are usually complex, and current algorithms are either not powerful enough or tend to over-fit. We make use of the kernel trick in combination with sparsification to provide a powerful function class for large data sets. Sparsity is achieved by a novel matching pursuit approach that can be applied to other tasks as well. For small but complex data sets, however, the kernel SFA approach leads to over-fitting and numerical instabilities. To enforce a stable solution, we introduce regularization to the SFA objective. Versatility and performance of our method are demonstrated on audio and video data sets.
U2 - 10.1007/978-3-642-23780-5_25
DO - 10.1007/978-3-642-23780-5_25
M3 - Conference contribution/Paper
SN - 9783642237799
T3 - Lecture Notes in Computer Science
SP - 235
EP - 248
BT - Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011
A2 - Gunopulos, D.
A2 - Hoffmann, T.
A2 - Malerba, D.
A2 - Vazirgiannis, M.
PB - Springer
CY - Berlin
ER -
