Manifold learning with iterative dimensionality photo-projection

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Standard

Manifold learning with iterative dimensionality photo-projection. / Luckehe, Daniel; Oehmcke, Stefan; Kramer, Oliver.

2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. s. 2555-2561 7966167.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt

Harvard

Luckehe, D, Oehmcke, S & Kramer, O 2017, Manifold learning with iterative dimensionality photo-projection. i 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings., 7966167, Institute of Electrical and Electronics Engineers Inc., s. 2555-2561, 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, USA, 14/05/2017. https://doi.org/10.1109/IJCNN.2017.7966167

APA

Luckehe, D., Oehmcke, S., & Kramer, O. (2017). Manifold learning with iterative dimensionality photo-projection. I 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings (s. 2555-2561). [7966167] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2017.7966167

Vancouver

Luckehe D, Oehmcke S, Kramer O. Manifold learning with iterative dimensionality photo-projection. I 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. s. 2555-2561. 7966167 https://doi.org/10.1109/IJCNN.2017.7966167

Author

Luckehe, Daniel ; Oehmcke, Stefan ; Kramer, Oliver. / Manifold learning with iterative dimensionality photo-projection. 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. s. 2555-2561

Bibtex

@inproceedings{1523895138924b4d8a004336693bc42b,
title = "Manifold learning with iterative dimensionality photo-projection",
abstract = "In this work, we propose a new dimensionality reduction approach for generating low-dimensional embeddings of high-dimensional data based on an iterative procedure. The data set's dimensions are sorted depending on their variance. Starting with the highest variance, the dimensions are iteratively projected onto the embedding. The projection can be seen as taking a photo from a two-dimensional motive employing a depth effect. The approach is flexible and offers numerous extensions for future work. We introduce a basic variant and illustrate it working mechanisms with numerous visualizations. The approach is experimentally analyzed on a small set of benchmark problems. Exemplary embeddings and evaluations based on the Shepard-Kruskal measure and the co-ranking matrix complement the analysis. The new approach shows competitive results in comparison to well-established dimensionality reduction methods.",
author = "Daniel Luckehe and Stefan Oehmcke and Oliver Kramer",
year = "2017",
month = jun,
day = "30",
doi = "10.1109/IJCNN.2017.7966167",
language = "English",
pages = "2555--2561",
booktitle = "2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",
note = "2017 International Joint Conference on Neural Networks, IJCNN 2017 ; Conference date: 14-05-2017 Through 19-05-2017",

}

RIS

TY - GEN

T1 - Manifold learning with iterative dimensionality photo-projection

AU - Luckehe, Daniel

AU - Oehmcke, Stefan

AU - Kramer, Oliver

PY - 2017/6/30

Y1 - 2017/6/30

N2 - In this work, we propose a new dimensionality reduction approach for generating low-dimensional embeddings of high-dimensional data based on an iterative procedure. The data set's dimensions are sorted depending on their variance. Starting with the highest variance, the dimensions are iteratively projected onto the embedding. The projection can be seen as taking a photo from a two-dimensional motive employing a depth effect. The approach is flexible and offers numerous extensions for future work. We introduce a basic variant and illustrate it working mechanisms with numerous visualizations. The approach is experimentally analyzed on a small set of benchmark problems. Exemplary embeddings and evaluations based on the Shepard-Kruskal measure and the co-ranking matrix complement the analysis. The new approach shows competitive results in comparison to well-established dimensionality reduction methods.

AB - In this work, we propose a new dimensionality reduction approach for generating low-dimensional embeddings of high-dimensional data based on an iterative procedure. The data set's dimensions are sorted depending on their variance. Starting with the highest variance, the dimensions are iteratively projected onto the embedding. The projection can be seen as taking a photo from a two-dimensional motive employing a depth effect. The approach is flexible and offers numerous extensions for future work. We introduce a basic variant and illustrate it working mechanisms with numerous visualizations. The approach is experimentally analyzed on a small set of benchmark problems. Exemplary embeddings and evaluations based on the Shepard-Kruskal measure and the co-ranking matrix complement the analysis. The new approach shows competitive results in comparison to well-established dimensionality reduction methods.

UR - http://www.scopus.com/inward/record.url?scp=85030868252&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2017.7966167

DO - 10.1109/IJCNN.2017.7966167

M3 - Article in proceedings

AN - SCOPUS:85030868252

SP - 2555

EP - 2561

BT - 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 International Joint Conference on Neural Networks, IJCNN 2017

Y2 - 14 May 2017 through 19 May 2017

ER -

ID: 223196256