Segment and combine: a generic approach for supervised learning of invariant classifiers from topologically structured data

Segment and combine: a generic approach for supervised learning of invariant classifiers from topologically structured data (2006)

Cached

Download Links

[www.montefiore.ulg.ac.be]

by Pierre Geurts , Raphaël Marée , Louis Wehenkel

Venue:	in Machine Learning Conference of Belgium and The Netherlands (Benelearn
Citations:	3 - 0 self

BibTeX

@INPROCEEDINGS{Geurts06segmentand,
    author = {Pierre Geurts and Raphaël Marée and Louis Wehenkel},
    title = {Segment and combine: a generic approach for supervised learning of invariant classifiers from topologically structured data},
    booktitle = {in Machine Learning Conference of Belgium and The Netherlands (Benelearn},
    year = {2006}
}

Bookmark

OpenURL

Abstract

A generic method for supervised classification of structured objects is presented. The approach induces a classifier by (i) deriving a surrogate dataset from a pre-classified dataset of structured objects, by segmenting them into pieces, (ii) learning a model relating pieces to object-classes, (iii) classifying structured objects by combining predictions made for their pieces. The segmentation allows to exploit local information and can be adapted to inject invariances into the resulting classifier. The framework is illustrated on practical sequence, time-series and image classification problems. 1.

Citations

2529	C.J.E.: Uci repository of machine learning databases, http://www.ics.uci.edu/ ∼ mlearn/MLRepository.html - Blake, Keogh
774	A performance evaluation of local descriptors - Mikolajczyk, Schmid - 2003
282	Text classification using string kernels - Lodhi, Saunders, et al. - 2002
149	A comparison of affine region detectors - Mikolajczyk, Tuytelaars, et al.
88	Extremely randomized trees - Geurts, Ernst, et al.
68	Local feature extraction and its applications using a library of bases - Saito - 1994
57	Random subwindows for robust image classification - Marée, Geurts, et al.
47	Dynamic time-alignment kernel in support vector machine - Shimodaira, Noma, et al. - 2001
45	Learning comprehensible descriptions of multivariate time series - Kadous - 1999
42	Making time-series classification more accurate using learned constraints - Ratanamahatana, Keogh
36	Pattern extraction for time series classification - Geurts - 2001
25	Automatic feature extraction for classifying audio data - Mierswa, Morik - 2005
16	Multidimensional Curve Classification Using PassingThrough Regions - Kudo, Toyama, et al. - 1999
15	Generalized feature extraction for structural pattern recognition in time-series data - Olszewski - 2001
13	Combining pattern discovery and discriminant analysis to predict gene co-regulation - Simonis, Wodak, et al. - 2004
12	Combinatorial motif analysis and hypothesis generation on a genomic scale - Hu, Sandmeyer, et al.
10	Decision-tree induction from time-series data based on standard-example split test - Yamada, Suzuki, et al. - 2003
9	New techniques for DNA sequence classification - Wang, Rozen, et al. - 1999
8	Classification of multivariate time series and structured data using constructive induction - Kadous, Sammut - 2005
7	Segment and combine approach for non-parametric time-series classification - Geurts, Wehenkel - 2005
4	Biomedical image classification with random subwindows and decision trees - Marée, Geurts, et al. - 2005
4	Feature selection for splice site prediction: a new method using eda-based feature ranking - Saeys, Degroeve, et al. - 2004
3	Boosting interval-based literals: Variable length and early classification - González, Rodríguez - 2002
3	The Divide-and-Conquer Manifesto”, Algorithmic Learning Theory - Dietterich - 2000
3	Segment and combine approach for biological sequence classification - Geurts, A, et al. - 2005
1	Akutsu (2004). Kernel methods in computational biology, chapter Local alignment kernels for biological sequences - Vert, Saigo