geoscience.net logo
+ Resolve Article
+ Follow Us
Follow on FacebookFollow on Facebook
Follow on TwitterFollow on Twitter

+ Translate
+ Subscribe to Site Feed
GeoScience Most Shared ContentMost Shared Content

Stochastic subset selection for learning with kernel machines


, : Stochastic subset selection for learning with kernel machines. IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics 42(3): 616-626

Kernel machines have gained much popularity in applications of machine learning. Support vector machines (SVMs) are a subset of kernel machines and generalize well for classification, regression, and anomaly detection tasks. The training procedure for traditional SVMs involves solving a quadratic programming (QP) problem. The QP problem scales super linearly in computational effort with the number of training samples and is often used for the offline batch processing of data. Kernel machines operate by retaining a subset of observed data during training. The data vectors contained within this subset are referred to as support vectors (SVs). The work presented in this paper introduces a subset selection method for the use of kernel machines in online, changing environments. Our algorithm works by using a stochastic indexing technique when selecting a subset of SVs when computing the kernel expansion. The work described here is novel because it separates the selection of kernel basis functions from the training algorithm used. The subset selection algorithm presented here can be used in conjunction with any online training technique. It is important for online kernel machines to be computationally efficient due to the real-time requirements of online environments. Our algorithm is an important contribution because it scales linearly with the number of training samples and is compatible with current training techniques. Our algorithm outperforms standard techniques in terms of computational efficiency and provides increased recognition accuracy in our experiments. We provide results from experiments using both simulated and real-world data sets to verify our algorithm.

US$19.90

PMID: 22049369

DOI: 10.1109/TSMCB.2011.2171680


Other references

Cali, V., 1955: Occupational urticaria from vegetable hair. Folia Medica. Folia Medica 38(1): 17-25

Bren, K.L.; Patel, K.; Fee, J.A., 1999: Paramagnetic 1H NMR investigation of recombinant T thermophilus cytochromes c. Journal of Inorganic Biochemistry 74(1-4): 82, April 30

Callender, D., 2006: Vaccine shortages: implications for pediatric nurse practitioners. Journal of Pediatric Health Care 20(6): 426-429

Golinska, Zofia, E., 2003: Wystepowanie nowych gatunkow rodzaju Trichinella u zwierzat i ludzi. Recent information on the occurrence of new species of Trichinella genus is included in this review. More attention is paid to the non-encapsulated species. The present taxonomic revision of the genus Trichinella is based primarily on genetic anal...

Izzo I.; D.M.tteo L.; Minucci S.; Iela L.; D.M.glio M.; Rastogi R.K., 1982: Control of the frog rana esculenta thumb pad. Extirpation of the pars distalis of the pituitary or castration in any period of the year causes thumb pad regression. Thumb pad development is regulated by an interaction of both temperature and androgenic hormones.

Martin-Comin, J.; Guardiola, J., 2012: Measuring SeHCAT retention: the use of a collimated gamma camera. Nuclear Medicine Communications 33(5): 521-521

Piao, Y.; Chen, X-Qun.; Liu, L-Mei.; Hong, L.; Liu, J-Hua.; Zhou, F.; Liu, Y-Qin., 2006: Reversion of multidrug resistance in HL-60/VCR cells by down-regulation of bcl-2 with bcl-2 siRNA. To evaluate the feasibility of gene therapy using bcl-2 as target in multiple drug resistance of leukemia, the small interfering RNA eukaryotic expression vector specific to human bcl-2 gene was constructed by gene recombination, then transfected...

Singh R.; Mall T.P., 1975: Effect of potato virus x on the free amino acids content of chenopodium amaranticolor leaves. Indian Phytopathology 28(1): 117-118

Viale, M.; Anzaldi, M.; Aiello, C.; Fenoglio, C.; Albicini, F.; Emionite, L.; Gangemi, R.; Balbi, A., 2014: Evaluation of the anti-proliferative activity of three new pyrazole compounds in sensitive and resistant tumor cell lines. In previous papers we demonstrated that the activity of short heteroretinoids as anti-proliferative and pro-apoptotic compounds was deeply linked to their heterocyclic moiety and that ionone-derived 1,5-pyrazoles had the highest anti-proliferative...

Miropolsky L.M., 1945: In memory of A. E. Fersman. A biographical sketch of A. E. Fersman (1883-1945).